© 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. 3171
    Prev
    Next
    INDEX
    Explanations

    mentions of legal, political, and societal issues

    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
    +0.25
    1.2%
    82
    +0.11
    0.5%
    701
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.25
    0.07
    25
    +0.11
    0.04
    547
    +0.11
    0.04
    Negative Logits
    ulas
    -0.65
    }}}
    -0.64
    isitions
    -0.64
    ategories
    -0.63
    ittens
    -0.61
    ults
    -0.60
    cult
    -0.59
    doms
    -0.59
    iencies
    -0.57
    auts
    -0.57
    POSITIVE LOGITS
     whereby
    1.25
     titled
    1.02
     wherein
    1.01
     indicating
    0.98
     involving
    0.89
     outlining
    0.89
     consisting
    0.86
     featuring
    0.82
     illustrating
    0.79
     depicting
    0.79
    Activations Density 0.721%

    No Known Activations