© 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 49152
    9. 8-RES_FS49152-JB
    11. 37383
    Prev
    Next
    INDEX
    Explanations

    actions related to harm and injury

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    481
    +0.14
    0.6%
    665
    +0.12
    0.6%
    447
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.14
    0.06
    351
    +0.12
    0.04
    125
    +0.12
    0.04
    Negative Logits
    arij
    -0.59
     AU
    -0.57
     LOT
    -0.56
     sourcing
    -0.56
    ibia
    -0.56
     acron
    -0.55
    ARE
    -0.54
    ajo
    -0.54
     Bei
    -0.54
     Horton
    -0.54
    POSITIVE LOGITS
     by
    1.09
    ooter
    0.76
    otyp
    0.75
    ptin
    0.74
     By
    0.72
    ission
    0.72
    by
    0.72
     alive
    0.71
     elsewhere
    0.71
    entary
    0.71
    Activations Density 0.134%

    No Known Activations