© 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 12288
    9. 8-RES_FS12288-JB
    11. 10249
    Prev
    Next
    INDEX
    Explanations

    titles or headings emphasized by the word "title"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    484
    +0.12
    0.5%
    678
    +0.10
    0.5%
    339
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.12
    0.03
    437
    +0.10
    0.02
    678
    +0.10
    0.02
    Negative Logits
    gm
    -0.76
     Spice
    -0.68
    ratom
    -0.68
    apons
    -0.65
    istani
    -0.65
    ombo
    -0.63
    addafi
    -0.63
     Leone
    -0.63
    akia
    -0.63
    olson
    -0.62
    POSITIVE LOGITS
    manship
    0.96
    marks
    0.89
    plates
    0.85
    title
    0.83
    plate
    0.81
    ¥µ
    0.81
    holder
    0.78
     deeds
    0.78
    mark
    0.78
    holders
    0.76
    Activations Density 0.057%

    No Known Activations