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 3072
    5. 8-RES_FS3072-JB
    6. 2749
    Prev
    Next
    INDEX
    Explanations

    URLs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    496
    +0.13
    0.6%
    373
    +0.12
    0.6%
    766
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.13
    0.06
    586
    +0.12
    0.06
    284
    +0.12
    0.07
    Negative Logits
     Paw
    -0.71
     Boo
    -0.69
     Ending
    -0.69
     Rath
    -0.67
     Gillespie
    -0.67
     Malone
    -0.66
     Conclusion
    -0.66
     Rats
    -0.66
     Ribbon
    -0.65
     Pants
    -0.65
    POSITIVE LOGITS
    cdn
    1.25
    forums
    1.02
    online
    1.00
    archives
    0.99
    cms
    0.90
    wiki
    0.90
    foundation
    0.89
    ecd
    0.89
    archive
    0.88
    /?
    0.87
    Activations Density 0.589%

    No Known Activations