© 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 EvalsExportsinterp-engineNEWAPI 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. 13794
    Prev
    Next
    INDEX
    Explanations

    names of sports players and teams

    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
    393
    +0.12
    0.6%
    83
    +0.11
    0.5%
    640
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.12
    0.04
    308
    +0.11
    0.03
    145
    +0.11
    0.03
    Negative Logits
    bered
    -0.78
     eaves
    -0.76
    omething
    -0.76
    rave
    -0.72
    inement
    -0.70
     tremend
    -0.70
    vre
    -0.69
     inward
    -0.69
    aston
    -0.65
    SPONSORED
    -0.65
    POSITIVE LOGITS
     None
    1.18
     Unknown
    1.14
     TBA
    1.13
     TBD
    1.08
     ???
    1.02
     Nope
    0.97
     Ibid
    0.95
     Various
    0.95
     Yes
    0.90
     Provided
    0.90
    Activations Density 0.100%

    No Known Activations