© 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. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 31295
    Prev
    Next
    INDEX
    Explanations

    mentions of people in groups

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.27
    1.7%
    481
    +0.12
    0.7%
    553
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.27
    0.29
    553
    +0.12
    0.10
    336
    +0.10
    0.08
    Negative Logits
     RTX
    -0.56
    âĢ¢âĢ¢
    -0.51
    Rush
    -0.50
    Press
    -0.49
    politics
    -0.49
    Deal
    -0.48
    Chain
    -0.47
    mire
    -0.47
    Charg
    -0.47
    Fine
    -0.46
    POSITIVE LOGITS
    atic
    0.73
    atically
    0.69
     selves
    0.63
     perished
    0.56
     clustered
    0.55
     succeeded
    0.54
     curses
    0.53
     sprinkled
    0.53
    selves
    0.52
     numbered
    0.52
    Activations Density 12.070%

    No Known Activations