© 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. 9045
    Prev
    Next
    INDEX
    Explanations

    companies, organizations, locations, and events mentioned in news articles

    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
    216
    +0.13
    0.6%
    585
    +0.10
    0.5%
    451
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    185
    +0.13
    0.03
    216
    +0.10
    0.03
    451
    +0.10
    0.03
    Negative Logits
    fen
    -0.83
    fy
    -0.78
    jad
    -0.76
    facing
    -0.76
    skirts
    -0.74
    ious
    -0.73
    chy
    -0.72
    bara
    -0.70
    lik
    -0.70
     Mub
    -0.69
    POSITIVE LOGITS
     (>
    0.93
    gest
    0.92
     chunk
    0.91
     shareholder
    0.86
     swath
    0.86
     gathering
    0.84
     creditor
    0.83
     collection
    0.82
     contiguous
    0.81
     scale
    0.81
    Activations Density 0.027%

    No Known Activations