© 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. 8851
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a sense of having had enough or sufficient of something

    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
    437
    +0.02
    0.5%
    396
    +0.02
    0.5%
    147
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.02
    0.03
    373
    +0.02
    -0.02
    513
    +0.02
    0.02
    Negative Logits
    20439
    -0.17
    Interstitial
    -0.16
    Introduced
    -0.15
    swick
    -0.15
    wcsstore
    -0.15
    ciating
    -0.15
    stri
    -0.14
    IFT
    -0.14
    ptions
    -0.14
    artifacts
    -0.14
    POSITIVE LOGITS
     mathemat
    0.20
    ipolar
    0.17
     tyr
    0.15
     Palest
    0.14
     Pry
    0.14
     welf
    0.14
     automation
    0.14
     scient
    0.13
    ilia
    0.13
     redes
    0.13
    Activations Density 0.200%

    No Known Activations