© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15662
    Prev
    Next
    INDEX
    Explanations

    sport-related achievements or results

    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
    373
    +0.11
    0.5%
    430
    +0.10
    0.4%
    371
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    506
    +0.11
    0.03
    371
    +0.10
    0.03
    555
    +0.09
    0.03
    Negative Logits
    pmwiki
    -0.81
    Marx
    -0.74
    dial
    -0.71
    direction
    -0.67
    Values
    -0.66
     informants
    -0.66
    INFO
    -0.65
     COUNTY
    -0.65
     jurisd
    -0.64
    Reference
    -0.64
    POSITIVE LOGITS
     Jamie
    0.85
     Shaun
    0.79
     Alex
    0.76
     Gina
    0.76
     Akira
    0.76
     Connor
    0.75
     Eddie
    0.74
     Tony
    0.74
     Reggie
    0.74
     Steph
    0.74
    Activations Density 0.125%

    No Known Activations