© 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. 13915
    Prev
    Next
    INDEX
    Explanations

    names of athletes in a team roster

    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
    93
    +0.14
    0.6%
    188
    +0.10
    0.4%
    40
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.14
    0.03
    469
    +0.10
    0.02
    176
    +0.09
    0.02
    Negative Logits
     unsur
    -0.77
    ageddon
    -0.75
    orously
    -0.74
    meet
    -0.74
    riv
    -0.73
    Ô
    -0.71
    indust
    -0.71
    Discover
    -0.69
     Qué
    -0.69
     Ange
    -0.68
    POSITIVE LOGITS
     QB
    1.22
     fullback
    1.15
     LB
    1.12
     linebacker
    1.07
     RHP
    1.07
     quarterback
    1.03
     DEFENSE
    1.02
     cornerback
    1.02
     catcher
    1.01
     MLB
    0.98
    Activations Density 0.120%

    No Known Activations