© 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. 474
    Prev
    Next
    INDEX
    Explanations

    responses and replies to various requests for comments and urgent matters

    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
    254
    +0.10
    0.5%
    181
    +0.10
    0.5%
    499
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.10
    0.06
    499
    +0.10
    0.03
    181
    +0.09
    0.04
    Negative Logits
     ILCS
    -0.72
    kil
    -0.70
    hered
    -0.68
    termin
    -0.66
    safe
    -0.64
    utical
    -0.63
    riet
    -0.63
    conserv
    -0.63
    artifacts
    -0.62
     Procedure
    -0.62
    POSITIVE LOGITS
     requests
    1.22
     criticisms
    1.22
     criticism
    1.21
     queries
    1.15
     inquiries
    1.13
     questions
    1.07
     complaints
    1.04
     suggestions
    0.98
     critiques
    0.97
     accusations
    0.96
    Activations Density 0.351%

    No Known Activations