© 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. 36896
    Prev
    Next
    INDEX
    Explanations

    specific references to "Lynch" and the TV show "Twin Peaks"

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.14
    1.1%
    326
    +0.08
    0.6%
    288
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    709
    +0.14
    0.12
    326
    +0.08
    0.24
    649
    +0.06
    0.01
    Negative Logits
     vit
    -0.48
     reconc
    -0.44
     Gujar
    -0.39
     inflamm
    -0.39
    !/
    -0.37
    Lex
    -0.36
     distinguishing
    -0.36
    unal
    -0.36
     intangible
    -0.36
    onsense
    -0.34
    POSITIVE LOGITS
    burg
    0.58
    hao
    0.50
    orld
    0.49
    walker
    0.48
    wald
    0.46
     Lynch
    0.46
    seys
    0.46
    hart
    0.44
    bugs
    0.44
    brook
    0.43
    Activations Density 10.057%

    No Known Activations