© 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 12288
    9. 8-RES_FS12288-JB
    11. 1255
    Prev
    Next
    INDEX
    Explanations

    information about people passing away

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    373
    +0.15
    0.7%
    420
    +0.11
    0.5%
    430
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.15
    0.05
    438
    +0.11
    0.04
    545
    +0.11
    0.04
    Negative Logits
    sbm
    -0.76
    uman
    -0.74
    ãĥŃ
    -0.68
     Occupations
    -0.63
    ãĥ¯ãĥ³
    -0.62
    soDeliveryDate
    -0.62
     RGB
    -0.61
    alties
    -0.61
    ocular
    -0.61
    oun
    -0.61
    POSITIVE LOGITS
     aged
    0.94
     coroner
    0.92
     crem
    0.91
     tragically
    0.91
     mourn
    0.86
     pancreat
    0.81
     illness
    0.81
     psychiat
    0.80
    mortem
    0.80
     pneumonia
    0.80
    Activations Density 0.366%

    No Known Activations