© 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. 18941
    Prev
    Next
    INDEX
    Explanations

    instances of regulations, permissions, and requirements

    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
    665
    +0.12
    0.6%
    540
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.12
    0.06
    125
    +0.11
    0.04
    151
    +0.10
    0.05
    Negative Logits
     Sack
    -0.68
     TS
    -0.63
    FK
    -0.61
    tein
    -0.60
    TPS
    -0.59
    fish
    -0.58
     Pipeline
    -0.58
     Frag
    -0.58
     Zeit
    -0.58
    Allen
    -0.57
    POSITIVE LOGITS
    osta
    0.81
    eln
    0.73
    isexual
    0.72
    untarily
    0.72
     expend
    0.71
     liable
    0.69
    lig
    0.68
     aback
    0.68
    ghan
    0.66
     choose
    0.65
    Activations Density 0.178%

    No Known Activations