© 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. 2787
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "dawn."

    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
    538
    +0.17
    0.7%
    86
    +0.17
    0.7%
    288
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.13
    99
    +0.17
    0.09
    326
    +0.16
    0.10
    Negative Logits
    uana
    -0.98
    ttle
    -0.94
    ourke
    -0.92
     suscept
    -0.90
    amins
    -0.86
    ombs
    -0.86
    ========
    -0.86
    colo
    -0.85
    glomer
    -0.85
    hett
    -0.84
    POSITIVE LOGITS
    hower
    1.23
    hurst
    1.11
     Sparkle
    1.07
    flower
    1.00
    flake
    0.99
    bringer
    0.96
    issance
    0.96
    shire
    0.96
     Sloan
    0.95
    mare
    0.94
    Activations Density 1.594%

    No Known Activations