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

    Neuronpedia

    Jacobian LensNEW
    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. 12726
    Prev
    Next
    INDEX
    Explanations

    statements or descriptions indicating something is eternal or lasting indefinitely

    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
    706
    +0.12
    0.5%
    727
    +0.10
    0.4%
    269
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    706
    +0.12
    0.01
    303
    +0.10
    0.01
    727
    +0.10
    0.01
    Negative Logits
     Cosponsors
    -0.97
    anooga
    -0.97
    Cu
    -0.84
    annis
    -0.81
    sonian
    -0.69
    aspx
    -0.69
    rera
    -0.68
    umbn
    -0.67
    acist
    -0.67
    ioch
    -0.67
    POSITIVE LOGITS
    more
    1.07
    lasting
    0.96
     ago
    0.91
    green
    0.86
     thereafter
    0.81
    ãĤ£
    0.78
    forth
    0.73
    theless
    0.72
     å¤
    0.71
    changed
    0.69
    Activations Density 0.019%

    No Known Activations