© 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. 10513
    Prev
    Next
    INDEX
    Explanations

    functions and methods in coding examples

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    677
    +0.04
    0.4%
    80
    +0.04
    0.4%
    358
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.04
    0.01
    700
    +0.04
    0.01
    31
    +0.04
    0.01
    Negative Logits
    LEASE
    -0.32
     rejo
    -0.31
     Substance
    -0.31
     poll
    -0.31
    amera
    -0.29
     restart
    -0.28
    ipher
    -0.28
    mort
    -0.28
     survey
    -0.28
     awake
    -0.27
    POSITIVE LOGITS
    undai
    0.33
    reditary
    0.32
    handled
    0.31
    ilaterally
    0.30
    dollar
    0.30
     Leban
    0.29
    idth
    0.28
     Palest
    0.28
    seeing
    0.28
    ãĤ¤ãĥĪ
    0.28
    Activations Density 0.003%

    No Known Activations