© 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. 8785
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or criminal activities

    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
    480
    +0.61
    3.6%
    447
    +0.19
    1.1%
    266
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.61
    0.03
    266
    +0.19
    0.12
    195
    +0.15
    0.03
    Negative Logits
    .","
    -0.57
     ."
    -0.56
    +.
    -0.56
    .</
    -0.55
    $.
    -0.53
    +(
    -0.52
    *.
    -0.51
    milo
    -0.51
     ..."
    -0.50
     [(
    -0.50
    POSITIVE LOGITS
     meanwhile
    0.58
    odore
    0.55
    resa
    0.54
     Canaver
    0.52
     GOODMAN
    0.50
     Chomsky
    0.45
     irony
    0.45
     transcript
    0.45
     HuffPost
    0.44
     Hopkins
    0.44
    Activations Density 1.732%

    No Known Activations