© 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. 436
    Prev
    Next
    INDEX
    Explanations

    information related to sports trades and events

    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
    188
    +0.11
    0.5%
    314
    +0.10
    0.4%
    90
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    637
    +0.11
    0.05
    90
    +0.10
    0.05
    362
    +0.10
    0.06
    Negative Logits
    âĿ
    -0.68
    orage
    -0.63
    Ľ
    -0.62
    REP
    -0.57
     Defenders
    -0.56
    xit
    -0.56
    tif
    -0.56
     ©
    -0.55
    Capture
    -0.54
    enance
    -0.54
    POSITIVE LOGITS
    lining
    0.84
    _-
    0.82
     which
    0.82
    which
    0.82
     whom
    0.81
     spite
    0.78
    ardless
    0.78
    cluding
    0.77
    clud
    0.71
    cause
    0.71
    Activations Density 0.428%

    No Known Activations