© 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. 9071
    Prev
    Next
    INDEX
    Explanations

    instances where someone is unable to do something or faces obstacles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unable," often indicating a lack of ability or a situation where someone is prevented from doing something

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @jordan
    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
    490
    +0.15
    0.6%
    718
    +0.13
    0.5%
    311
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.15
    0.06
    665
    +0.13
    0.06
    746
    +0.12
    0.04
    Negative Logits
     Tradition
    -0.89
    VERTISEMENT
    -0.89
    enegger
    -0.81
    osate
    -0.80
     Alone
    -0.78
     che
    -0.78
     VIDEOS
    -0.77
    ERN
    -0.75
    algia
    -0.74
    article
    -0.73
    POSITIVE LOGITS
    ioned
    1.25
    ison
    1.16
    reys
    1.16
    ions
    1.05
    isons
    0.95
    bodied
    0.92
    itud
    0.90
    istically
    0.90
     Morrison
    0.89
    't
    0.89
    Activations Density 0.608%

    No Known Activations