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. 43344
    Prev
    Next
    INDEX
    Explanations

    terms related to particle physics and scientific experiments

    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
    519
    +0.11
    0.5%
    346
    +0.11
    0.5%
    271
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.11
    0.01
    325
    +0.11
    0.01
    288
    +0.10
    0.01
    Negative Logits
    agements
    -0.74
     Styles
    -0.73
     indic
    -0.73
    styles
    -0.72
     Conquest
    -0.72
    fur
    -0.70
    BuyableInstoreAndOnline
    -0.70
    meal
    -0.69
    vict
    -0.68
    kins
    -0.66
    POSITIVE LOGITS
     Collider
    1.34
     physicist
    1.33
     physicists
    1.32
    ERN
    0.96
    iggs
    0.94
     physics
    0.93
     Physics
    0.93
     particle
    0.92
     bos
    0.90
     Laboratory
    0.89
    Activations Density 0.033%

    No Known Activations