© 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. 37033
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, particularly related to individuals

    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
    +0.17
    0.8%
    721
    +0.13
    0.6%
    339
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    95
    +0.17
    0.06
    149
    +0.13
    0.04
    339
    +0.13
    0.07
    Negative Logits
    MpServer
    -0.77
    ħĭ
    -0.74
    displayText
    -0.71
    utra
    -0.69
    quished
    -0.68
    ORPG
    -0.68
    Newsletter
    -0.67
    é¾įåĸļ士
    -0.67
    anca
    -0.65
    ¥µ
    -0.65
    POSITIVE LOGITS
    ows
    0.91
    power
    0.91
    kie
    0.88
    iam
    0.85
    liam
    0.84
    ingham
    0.83
    ingly
    0.83
     Arn
    0.81
    sburg
    0.80
    fulness
    0.73
    Activations Density 9.769%

    No Known Activations