© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37212
    Prev
    Next
    INDEX
    Explanations

    URLs or links in the text

    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
    480
    +0.16
    0.8%
    443
    +0.14
    0.7%
    151
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.16
    0.01
    381
    +0.14
    0.01
    412
    +0.09
    0.01
    Negative Logits
    anwhile
    -0.94
    eday
    -0.75
     prest
    -0.71
     corrid
    -0.66
    icter
    -0.65
     ende
    -0.64
    */
    -0.62
     helicop
    -0.61
    terday
    -0.60
     adjourn
    -0.60
    POSITIVE LOGITS
    tv
    0.93
    www
    0.89
    ://
    0.83
    steam
    0.83
    books
    0.77
    twitter
    0.73
    ãĥ¼ãĥ
    0.71
    pmwiki
    0.68
    à¨
    0.65
    isSpecialOrderable
    0.65
    Activations Density 0.007%

    No Known Activations