© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2958
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cry" or related terms in the text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    102
    +0.19
    0.6%
    383
    +0.19
    0.6%
    178
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.19
    0.06
    288
    +0.19
    0.06
    85
    +0.18
    0.04
    Negative Logits
     nomine
    -1.25
    awaru
    -1.11
    ajo
    -1.02
    folios
    -1.01
    ulty
    -0.99
    ratulations
    -0.99
    efficients
    -0.99
    MG
    -0.96
    ammy
    -0.92
    emonium
    -0.91
    POSITIVE LOGITS
    stals
    1.83
    sis
    1.49
    baby
    1.36
    stall
    1.33
    pter
    1.26
    stal
    1.26
    chenko
    1.17
    ogen
    1.12
    tags
    1.11
    bot
    1.08
    Activations Density 0.833%

    No Known Activations