© 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. 1621
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in legal disputes

    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
    227
    +0.10
    0.4%
    77
    +0.09
    0.4%
    333
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.10
    0.02
    430
    +0.09
    0.02
    21
    +0.09
    0.02
    Negative Logits
     destro
    -0.81
     skelet
    -0.79
     tyr
    -0.79
     stewards
    -0.78
     enthusi
    -0.77
    ÃĥÃĤ
    -0.77
    sole
    -0.74
     appre
    -0.71
    ussion
    -0.71
     elig
    -0.70
    POSITIVE LOGITS
     Fiorina
    0.86
     Hyde
    0.83
     Pill
    0.82
     Jill
    0.82
     Mae
    0.81
     Lynch
    0.78
     Pelosi
    0.77
     Vest
    0.77
     Sunshine
    0.74
     Buk
    0.74
    Activations Density 0.019%

    No Known Activations