© 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. 1586
    Prev
    Next
    INDEX
    Explanations

    links to URL addresses

    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
    87
    +0.20
    1.0%
    756
    +0.14
    0.7%
    459
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.20
    0.05
    639
    +0.14
    0.04
    289
    +0.09
    0.01
    Negative Logits
    ĸļ
    -0.71
    xual
    -0.68
    actionDate
    -0.63
    soDeliveryDate
    -0.56
    govtrack
    -0.56
    worldly
    -0.55
    cffffcc
    -0.54
    earchers
    -0.53
    20439
    -0.52
     throats
    -0.51
    POSITIVE LOGITS
    heit
    0.73
     Speedway
    0.54
    inet
    0.53
     reign
    0.50
    iland
    0.50
    iola
    0.49
    inery
    0.49
     Robinson
    0.47
    igi
    0.47
     SetFontSize
    0.47
    Activations Density 0.583%

    No Known Activations