© 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. 2606
    Prev
    Next
    INDEX
    Explanations

    words related to accidents, incidents, tragedies, and deaths, including specific mentions of various types of accidents

    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
    288
    +0.23
    0.9%
    151
    +0.18
    0.7%
    762
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.15
    151
    +0.18
    0.12
    762
    +0.15
    0.10
    Negative Logits
    ebus
    -1.04
    ongyang
    -1.04
    secut
    -1.03
    gemony
    -1.01
    unda
    -0.99
    ularity
    -0.98
    hett
    -0.97
    orney
    -0.95
    erion
    -0.93
    uggish
    -0.93
    POSITIVE LOGITS
     accident
    1.07
     accidents
    0.99
    worthiness
    0.97
    ously
    0.94
     hazard
    0.90
     occ
    0.88
     MH
    0.86
     involving
    0.86
     Reincarn
    0.83
     Odyssey
    0.83
    Activations Density 1.793%

    No Known Activations