© 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. 3063
    Prev
    Next
    INDEX
    Explanations

    mentions and descriptions of mysterious events or situations

    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
    288
    +0.17
    0.6%
    744
    +0.15
    0.5%
    549
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.08
    744
    +0.15
    0.06
    613
    +0.14
    0.05
    Negative Logits
    ibaba
    -1.09
    attery
    -1.01
    arf
    -1.00
    sen
    -0.99
    obe
    -0.98
    acus
    -0.94
    ombo
    -0.93
    onia
    -0.90
    ocations
    -0.89
    ioch
    -0.89
    POSITIVE LOGITS
     Flavoring
    1.13
     Mystery
    1.12
    ulously
    1.05
     mystery
    1.04
     mysteries
    1.00
     solved
    1.00
     Mysteries
    0.98
    crow
    0.91
     Scythe
    0.89
     surrounds
    0.88
    Activations Density 0.688%

    No Known Activations