© 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. 37342
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating relationships or connections

    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
    362
    +0.12
    0.6%
    692
    +0.11
    0.5%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    692
    +0.12
    0.02
    362
    +0.11
    0.02
    750
    +0.11
    0.02
    Negative Logits
    incial
    -0.89
    afia
    -0.75
    idences
    -0.73
    ederal
    -0.71
    cci
    -0.70
    merce
    -0.70
    ossibility
    -0.70
    anguage
    -0.70
    aren
    -0.69
    ignt
    -0.69
    POSITIVE LOGITS
     nowhere
    0.71
     Rowe
    0.67
     mole
    0.65
     Gillespie
    0.64
     Bris
    0.63
     Buster
    0.61
     existence
    0.60
     him
    0.59
     everything
    0.59
     them
    0.58
    Activations Density 0.025%

    No Known Activations