© 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. 37393
    Prev
    Next
    INDEX
    Explanations

    references to governors and their actions or decisions

    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
    71
    +0.13
    0.6%
    238
    +0.13
    0.6%
    314
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.13
    0.02
    224
    +0.13
    0.02
    146
    +0.12
    0.02
    Negative Logits
     Warfare
    -0.68
    llah
    -0.67
    origin
    -0.66
     Pieces
    -0.66
    theless
    -0.65
    obyl
    -0.64
    mble
    -0.64
    schild
    -0.63
     Wrap
    -0.63
    eners
    -0.62
    POSITIVE LOGITS
     governor
    0.91
     Governor
    0.86
     vetoed
    0.84
     Cuomo
    0.81
    Govern
    0.77
    ates
    0.74
     appoint
    0.73
    esses
    0.73
     gubernatorial
    0.71
    externalActionCode
    0.70
    Activations Density 0.014%

    No Known Activations