© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1633
    Prev
    Next
    INDEX
    Explanations

    Twitter activity from various individuals

    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
    430
    +0.13
    0.6%
    396
    +0.11
    0.5%
    132
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.13
    0.04
    13
    +0.11
    0.04
    547
    +0.10
    0.03
    Negative Logits
     Dracula
    -0.67
    hov
    -0.64
    inventoryQuantity
    -0.62
     zoning
    -0.61
     incumb
    -0.61
     licens
    -0.61
     Trials
    -0.61
     clitor
    -0.60
    vantage
    -0.60
    ptin
    -0.60
    POSITIVE LOGITS
     yesterday
    0.88
    realDonaldTrump
    0.79
     today
    0.76
    Yesterday
    0.76
    storm
    0.73
     "@
    0.72
    Tweet
    0.72
     congrat
    0.72
    oulder
    0.71
     sarcast
    0.71
    Activations Density 0.053%

    No Known Activations