© 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. 23893
    Prev
    Next
    INDEX
    Explanations

    references to the American Civil War

    oai_token-act-pair · gpt-4o-miniTriggered 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
    288
    +0.16
    0.7%
    314
    +0.12
    0.5%
    113
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.16
    0.02
    752
    +0.12
    0.02
    113
    +0.11
    0.02
    Negative Logits
    cca
    -0.70
     Canaver
    -0.63
    ï¸ı
    -0.62
     forged
    -0.62
    agame
    -0.61
    lihood
    -0.61
    prime
    -0.61
    posts
    -0.60
    ugi
    -0.60
    rams
    -0.60
    POSITIVE LOGITS
    izational
    1.21
     Liberties
    1.10
    izations
    0.94
    isations
    0.93
    ization
    0.93
    ized
    0.90
    isation
    0.89
    ian
    0.89
    ians
    0.89
     Rights
    0.87
    Activations Density 0.009%

    No Known Activations