© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19720
    Prev
    Next
    INDEX
    Explanations

    information related to time, votes, and playthroughs

    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
    373
    +0.16
    0.8%
    530
    +0.12
    0.6%
    159
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.16
    0.03
    545
    +0.12
    0.03
    460
    +0.11
    0.03
    Negative Logits
    atically
    -0.69
     distur
    -0.67
    rums
    -0.66
    llah
    -0.66
     mism
    -0.64
    gat
    -0.63
     predec
    -0.62
    enance
    -0.61
    reditary
    -0.61
    bing
    -0.60
    POSITIVE LOGITS
     Ago
    1.03
     ago
    0.83
     Views
    0.80
    Reviewed
    0.77
     Duration
    0.75
     IST
    0.73
    NES
    0.70
     PID
    0.70
     Difficulty
    0.68
    Date
    0.67
    Activations Density 0.095%

    No Known Activations