© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 20185
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and specific players

    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
    459
    +0.13
    0.6%
    241
    +0.10
    0.5%
    544
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.13
    0.06
    506
    +0.10
    0.04
    401
    +0.10
    0.05
    Negative Logits
    "},"
    -0.59
     attm
    -0.58
     eternity
    -0.57
     Mehran
    -0.57
     Authorization
    -0.57
     Grateful
    -0.56
     likeness
    -0.54
     UID
    -0.53
     Amen
    -0.53
     Masonic
    -0.52
    POSITIVE LOGITS
     likewise
    1.22
     meanwhile
    1.09
     fared
    1.07
     similarly
    0.92
     went
    0.90
     gave
    0.89
     did
    0.86
     got
    0.86
     took
    0.86
     has
    0.85
    Activations Density 0.328%

    No Known Activations