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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19028
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "steel"

    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
    288
    +0.10
    0.5%
    736
    +0.10
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.10
    0.01
    326
    +0.10
    0.01
    411
    +0.10
    0.01
    Negative Logits
    uate
    -0.78
    sembly
    -0.75
     Kard
    -0.73
     Garr
    -0.68
     Niet
    -0.67
    aminer
    -0.67
    romeda
    -0.65
     RTX
    -0.64
     Gohan
    -0.64
    cffffcc
    -0.63
    POSITIVE LOGITS
    Series
    1.18
    workers
    1.17
    works
    1.14
    worker
    1.08
     wool
    1.01
    clad
    0.94
     beams
    0.92
    steel
    0.88
    fish
    0.87
     oxide
    0.85
    Activations Density 0.014%

    No Known Activations