© 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. 4007
    Prev
    Next
    INDEX
    Explanations

    negative actions, experiences, or criticism related to politics or society

    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
    505
    +0.11
    0.5%
    236
    +0.10
    0.5%
    489
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.11
    0.04
    505
    +0.10
    0.03
    90
    +0.10
    0.03
    Negative Logits
    kefeller
    -0.64
     easing
    -0.56
    ingers
    -0.56
     Guid
    -0.55
     Tsukuyomi
    -0.55
     Queens
    -0.53
     Parables
    -0.53
    ultimate
    -0.52
     Fortress
    -0.52
    ppings
    -0.51
    POSITIVE LOGITS
     etc
    0.80
    âĶĢâĶĢâĶĢâĶĢ
    0.73
    ,
    0.70
    rote
    0.69
    etc
    0.68
    scribe
    0.63
    ei
    0.62
    oret
    0.62
    cler
    0.62
    !,
    0.62
    Activations Density 0.126%

    No Known Activations