© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11233
    Prev
    Next
    INDEX
    Explanations

    instances of physical combat or confrontation in a narrative or description

    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
    384
    +0.14
    0.5%
    612
    +0.13
    0.5%
    35
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.14
    0.09
    366
    +0.13
    0.07
    553
    +0.13
    0.07
    Negative Logits
    uci
    -0.94
    atl
    -0.93
    lux
    -0.90
    Ô
    -0.90
    oola
    -0.89
    ="#
    -0.88
    mun
    -0.86
     Williamson
    -0.85
     Helsinki
    -0.83
    2020
    -0.82
    POSITIVE LOGITS
    worldly
    1.14
     counterpart
    0.97
     counterparts
    0.95
     baseman
    0.94
    dayName
    0.94
     contestant
    0.93
    ;
    0.92
     incarn
    0.91
     thereof
    0.87
     branch
    0.85
    Activations Density 2.195%

    No Known Activations