© 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. 10143
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns related to political figures, historical events, and legal proceedings

    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
    167
    +0.11
    0.5%
    67
    +0.10
    0.5%
    435
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.01
    170
    +0.10
    0.01
    382
    +0.09
    0.01
    Negative Logits
    PsyNetMessage
    -0.95
    igslist
    -0.82
    anwhile
    -0.71
     GEAR
    -0.70
     mileage
    -0.69
    anova
    -0.67
    icably
    -0.66
    aeda
    -0.65
    UTE
    -0.65
    URA
    -0.65
    POSITIVE LOGITS
    ewater
    1.35
    eness
    1.18
    bread
    1.09
    ened
    1.07
    eless
    1.07
    estone
    1.05
    ening
    1.04
    acre
    1.02
    ney
    1.01
    comb
    1.01
    Activations Density 0.016%

    No Known Activations