Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 12207
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns indicating ownership or association

    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
    489
    +0.11
    0.5%
    362
    +0.11
    0.5%
    274
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.04
    489
    +0.11
    0.04
    562
    +0.10
    0.03
    Negative Logits
    escription
    -0.84
    cerpt
    -0.74
    lement
    -0.72
    ̶
    -0.72
    irection
    -0.71
    glomer
    -0.70
    plin
    -0.69
    thood
    -0.68
    lehem
    -0.67
    itect
    -0.67
    POSITIVE LOGITS
     behalf
    1.61
     doorstep
    1.43
     own
    1.30
     heels
    1.25
     shoulders
    1.24
     knees
    1.21
     occasions
    1.06
     wrists
    1.05
     basis
    1.02
     campuses
    1.02
    Activations Density 0.054%

    No Known Activations