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 49152
    5. 8-RES_FS49152-JB
    6. 25619
    Prev
    Next
    INDEX
    Explanations

    words related to rebalance 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
    314
    +0.14
    0.7%
    521
    +0.09
    0.4%
    245
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.14
    0.01
    41
    +0.09
    0.01
    373
    +0.09
    -0.01
    Negative Logits
     Galile
    -0.69
     Bucc
    -0.63
    ©¶æ
    -0.60
     Neph
    -0.57
     Ys
    -0.57
     workforce
    -0.57
     Parenthood
    -0.56
     Vald
    -0.56
     pecul
    -0.56
     showc
    -0.55
    POSITIVE LOGITS
    strap
    0.88
    ruary
    0.82
    rocal
    0.82
    schild
    0.79
    iction
    0.75
    iates
    0.75
    alion
    0.73
    ancing
    0.73
    Cole
    0.72
    cipled
    0.72
    Activations Density 0.021%

    No Known Activations