© 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. 3826
    Prev
    Next
    INDEX
    Explanations

    terms related to legal standards associated with evidence-based decision-making

    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
    183
    +0.12
    0.5%
    57
    +0.10
    0.5%
    181
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    183
    +0.12
    0.02
    57
    +0.10
    0.02
    88
    +0.10
    0.02
    Negative Logits
    pmwiki
    -0.70
    nian
    -0.69
    ICAN
    -0.69
     WATCHED
    -0.66
    si
    -0.66
    Ped
    -0.66
    ãĤ·ãĥ£
    -0.66
    cu
    -0.65
    姫
    -0.62
     Assass
    -0.62
    POSITIVE LOGITS
    iche
    0.83
     bounds
    0.82
     comprehension
    0.82
     infancy
    0.80
     reach
    0.77
     Borders
    0.76
     reaching
    0.75
     mere
    0.73
     Reach
    0.72
     doubt
    0.69
    Activations Density 0.028%

    No Known Activations