© 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 49152
    9. 8-RES_FS49152-JB
    11. 37157
    Prev
    Next
    INDEX
    Explanations

    words that denote skepticism, questioning, or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    94
    +0.10
    0.5%
    588
    +0.08
    0.4%
    10
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    588
    +0.10
    0.04
    288
    +0.08
    0.04
    151
    +0.08
    0.04
    Negative Logits
    oother
    -0.78
    ilege
    -0.76
    rio
    -0.73
    obook
    -0.72
    hner
    -0.71
    ynthesis
    -0.69
    endment
    -0.69
    psey
    -0.68
    umbn
    -0.68
    othal
    -0.67
    POSITIVE LOGITS
     enough
    0.95
     ones
    0.80
     amounts
    0.79
     huh
    0.76
     alike
    0.76
     sounding
    0.71
     indeed
    0.71
     nonetheless
    0.71
     since
    0.70
     strokes
    0.70
    Activations Density 0.192%

    No Known Activations