© 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. 20443
    Prev
    Next
    INDEX
    Explanations

    requests for actions or information

    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
    642
    +0.11
    0.5%
    498
    +0.11
    0.5%
    321
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.11
    0.04
    321
    +0.11
    0.04
    70
    +0.10
    0.04
    Negative Logits
    VERTISEMENT
    -0.71
    aah
    -0.69
    sung
    -0.66
    incarn
    -0.65
    productive
    -0.65
    lived
    -0.64
    uded
    -0.63
    ership
    -0.63
    xual
    -0.63
    anuts
    -0.62
    POSITIVE LOGITS
     Judicial
    0.84
     lenders
    0.78
     justices
    0.75
     governors
    0.74
     submissions
    0.74
     jurors
    0.73
     courts
    0.73
     permission
    0.73
     legislators
    0.73
     scholars
    0.72
    Activations Density 0.123%

    No Known Activations