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. 43395
    Prev
    Next
    INDEX
    Explanations

    conjunctions and the word "and" in various contexts

    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
    430
    +0.10
    0.5%
    447
    +0.09
    0.4%
    404
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.10
    0.03
    703
    +0.09
    0.03
    284
    +0.09
    0.03
    Negative Logits
    Cola
    -0.76
    ryu
    -0.75
     Cosponsors
    -0.72
     Unleashed
    -0.72
    etts
    -0.71
    *:
    -0.70
    ãĥķãĤ¡
    -0.69
    âĦ¢
    -0.68
     Helpful
    -0.66
     Logged
    -0.65
    POSITIVE LOGITS
     starvation
    0.86
    riage
    0.82
     dying
    0.79
     destruction
    0.78
     gloom
    0.78
     imprisonment
    0.78
     mortality
    0.73
     grief
    0.73
     casualty
    0.73
     trib
    0.72
    Activations Density 0.109%

    No Known Activations