© 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. 3324
    Prev
    Next
    INDEX
    Explanations

    information related to urban planning and development projects

    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
    592
    +0.12
    0.5%
    333
    +0.10
    0.4%
    677
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.12
    0.06
    13
    +0.10
    0.05
    608
    +0.09
    0.06
    Negative Logits
    ife
    -0.85
    iquette
    -0.84
    aminer
    -0.84
     depress
    -0.76
    ocaust
    -0.75
     clich
    -0.75
    atz
    -0.74
    acists
    -0.74
     panic
    -0.74
     stereotype
    -0.73
    POSITIVE LOGITS
     jointly
    1.22
     indemn
    1.11
     financing
    1.09
     concess
    1.08
     royalties
    1.06
     consortium
    1.02
     âĤ¬
    1.02
     subcontract
    0.99
     reimburse
    0.99
     Funding
    0.97
    Activations Density 0.459%

    No Known Activations