© 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. 18063
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities 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
    762
    +0.15
    0.7%
    545
    +0.10
    0.5%
    325
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.15
    0.06
    283
    +0.10
    0.01
    375
    +0.10
    0.03
    Negative Logits
     Cosponsors
    -0.80
     Supporters
    -0.79
    ovy
    -0.75
     HTTPS
    -0.74
     Committees
    -0.74
     yourselves
    -0.74
    Preview
    -0.73
    Vote
    -0.71
    artisan
    -0.70
     sidx
    -0.69
    POSITIVE LOGITS
     untreated
    1.16
     uncontroll
    1.12
     medication
    1.12
     alcoholism
    1.08
     puberty
    1.08
     amput
    1.06
     worsened
    1.06
     addiction
    1.04
     psychiat
    1.02
     hallucinations
    1.01
    Activations Density 0.672%

    No Known Activations