© 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. 1419
    Prev
    Next
    INDEX
    Explanations

    numerical value followed by a unit of measurement

    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
    708
    +0.10
    0.4%
    564
    +0.09
    0.4%
    507
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.10
    0.04
    326
    +0.09
    0.03
    564
    +0.09
    0.03
    Negative Logits
    Austral
    -0.75
    advertising
    -0.70
    ticket
    -0.67
     committees
    -0.67
     scapego
    -0.66
    gotten
    -0.65
    liga
    -0.65
     resemb
    -0.63
    igning
    -0.63
    CVE
    -0.62
    POSITIVE LOGITS
     increments
    0.98
    elsius
    0.98
    renheit
    0.92
    +.
    0.90
    +,
    0.89
     (~
    0.82
     apiece
    0.80
    ilion
    0.79
     intervals
    0.79
    Hz
    0.78
    Activations Density 0.127%

    No Known Activations