© 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. 9818
    Prev
    Next
    INDEX
    Explanations

    mentions of specific events or situations

    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
    159
    +0.16
    0.8%
    393
    +0.13
    0.6%
    267
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.16
    0.12
    598
    +0.13
    0.06
    186
    +0.11
    0.07
    Negative Logits
    ãĤ¹ãĥĪ
    -0.84
    ARS
    -0.74
    ready
    -0.73
    adle
    -0.72
    Ñĥ
    -0.72
    unk
    -0.72
    istries
    -0.72
    omo
    -0.72
    oller
    -0.70
    anamo
    -0.69
    POSITIVE LOGITS
     week
    1.07
     guy
    1.03
     year
    0.95
     weekend
    0.95
     latest
    0.94
     month
    0.89
     incarnation
    0.85
     trope
    0.85
     particular
    0.83
     newest
    0.82
    Activations Density 0.275%

    No Known Activations