© 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. 15080
    Prev
    Next
    INDEX
    Explanations

    mentions of lifting bans or restrictions on certain activities or products

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    481
    +0.12
    0.6%
    608
    +0.10
    0.4%
    79
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.12
    0.03
    79
    +0.10
    0.03
    557
    +0.09
    0.03
    Negative Logits
    OGR
    -0.81
    DERR
    -0.72
    ¯¯
    -0.72
    POSE
    -0.69
    pac
    -0.69
    flies
    -0.68
    oof
    -0.67
    Champ
    -0.67
     partName
    -0.67
     Krish
    -0.66
    POSITIVE LOGITS
     imports
    1.10
    erous
    0.94
     enforcing
    0.84
     sale
    0.84
     accessing
    0.83
     greenhouse
    0.83
     importing
    0.83
     smoking
    0.81
     storing
    0.80
     discretionary
    0.80
    Activations Density 0.129%

    No Known Activations