© 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 Local
    9. 6-RES_SCL-AJT
    11. 37070
    Prev
    Next
    INDEX
    Explanations

    items or options to choose from in a list, potentially for review or selection

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.20
    1.1%
    195
    +0.10
    0.6%
    709
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.20
    0.12
    384
    +0.10
    0.06
    595
    +0.08
    0.06
    Negative Logits
    ccording
    -0.77
    etheless
    -0.77
    opausal
    -0.68
     thous
    -0.63
    aez
    -0.62
    zona
    -0.62
    ophers
    -0.62
    sembly
    -0.61
    izations
    -0.61
    izes
    -0.61
    POSITIVE LOGITS
    lihood
    0.87
    ings
    0.81
    weed
    0.78
    able
    0.78
    Maker
    0.74
    back
    0.72
    maker
    0.72
    board
    0.71
    down
    0.71
    boards
    0.69
    Activations Density 16.942%

    No Known Activations