© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 9412
    Prev
    Next
    INDEX
    Explanations

    references to political figures and activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    679
    +0.18
    0.8%
    430
    +0.14
    0.7%
    640
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.18
    0.11
    679
    +0.14
    0.11
    430
    +0.12
    0.10
    Negative Logits
     extinct
    -0.87
     expend
    -0.69
     peanuts
    -0.67
     upkeep
    -0.67
     estates
    -0.67
     docks
    -0.67
     barley
    -0.67
     landfall
    -0.66
     affili
    -0.66
     economical
    -0.65
    POSITIVE LOGITS
     Specifically
    1.32
     Asked
    1.30
     Included
    1.12
     Speaking
    1.11
     Among
    1.11
     Respond
    1.09
     Refer
    1.09
     Notably
    1.07
     Saying
    1.06
     During
    1.05
    Activations Density 0.400%

    No Known Activations