© 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 24576
    9. 8-RES_FS24576-JB
    11. 18884
    Prev
    Next
    INDEX
    Explanations

    mentions of specific political figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    579
    +0.11
    0.5%
    530
    +0.11
    0.5%
    641
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    579
    +0.11
    0.03
    232
    +0.11
    0.03
    530
    +0.10
    0.02
    Negative Logits
    channelAvailability
    -0.64
     separat
    -0.62
     CPC
    -0.60
     confines
    -0.59
     causation
    -0.56
     STATS
    -0.56
    BIP
    -0.55
    plings
    -0.55
    auga
    -0.55
    bourg
    -0.54
    POSITIVE LOGITS
    Wan
    0.86
    leck
    0.83
    orio
    0.81
    wald
    0.78
    uary
    0.78
    worldly
    0.76
    ratulations
    0.72
    actory
    0.70
    ugh
    0.70
    isoft
    0.68
    Activations Density 0.069%

    No Known Activations