Hidden State Manipulation
A causal intervention method in mechanistic interpretability research. It adjusts states along specific directions in the hidden representation space to amplify or suppress the encoding of a given factor, and observes changes in model output to provide causal evidence.
Timeline (last 90 days)
The researchers conducted hidden state steering experiments on six models of 7-9B parameters, and shifting hidden states along the direction corresponding to each factor changed the models' judgments as expected.
The hidden state steering experiments provide causal evidence that psycholinguistic factors such as commonness and distinctiveness are encoded inside the models, rather than being merely correlational observations.
Hidden state steering is a causal intervention method in mechanistic interpretability research that locates concept directions in hidden representation space and adds or subtracts vectors along that direction to amplify or suppress the strength of a factor's encoding.
All Facts (3)
The hidden state steering experiments provide causal evidence that psycholinguistic factors such as commonness and distinctiveness are encoded inside the models, rather than being merely correlational observations.
50%UnverifiedHidden state steering is a causal intervention method in mechanistic interpretability research that locates concept directions in hidden representation space and adds or subtracts vectors along that direction to amplify or suppress the strength of a factor's encoding.
50%UnverifiedThe researchers conducted hidden state steering experiments on six models of 7-9B parameters, and shifting hidden states along the direction corresponding to each factor changed the models' judgments as expected.
50%