© 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. 37361
    Prev
    Next
    INDEX
    Explanations

    colons, dashes, and specific formatting cues indicating structure or emphasis in 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
    373
    +0.12
    0.5%
    717
    +0.11
    0.5%
    187
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.12
    0.02
    365
    +0.11
    0.01
    359
    +0.10
    0.01
    Negative Logits
    ĸļ
    -0.68
    ught
    -0.66
     unanswered
    -0.66
    pora
    -0.65
     elim
    -0.64
     unfor
    -0.61
     rem
    -0.61
    ictionary
    -0.60
    ynamic
    -0.60
    sbm
    -0.60
    POSITIVE LOGITS
    cially
    0.83
    rosso
    0.82
    sylvania
    0.68
    auga
    0.65
    skirts
    0.65
    aldehyde
    0.64
    ilda
    0.64
    ë
    0.64
    ciating
    0.63
    nova
    0.62
    Activations Density 0.042%

    No Known Activations