© 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. 2401
    Prev
    Next
    INDEX
    Explanations

    words related to ropes, cords, and restraints

    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
    99
    +0.11
    0.5%
    635
    +0.11
    0.5%
    57
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.08
    288
    +0.11
    0.10
    99
    +0.11
    0.07
    Negative Logits
    hip
    -0.76
    riz
    -0.74
    oric
    -0.74
    arter
    -0.74
    love
    -0.74
    IRE
    -0.73
    ebook
    -0.70
    vy
    -0.69
    ica
    -0.69
    sol
    -0.68
    POSITIVE LOGITS
    yip
    0.78
     cords
    0.73
    mble
    0.71
     Resurrection
    0.70
     jumper
    0.69
    xual
    0.69
     gorilla
    0.67
    sembly
    0.66
     jumping
    0.65
     crane
    0.63
    Activations Density 0.888%

    No Known Activations