© 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. 10890
    Prev
    Next
    INDEX
    Explanations

    information related to races, competitions, tournaments, and winners in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    words related to competition rankings, especially focused on positions like "winner" and "runner-up"

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    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
    575
    +0.11
    0.5%
    727
    +0.09
    0.5%
    247
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.11
    326
    +0.09
    0.10
    575
    +0.09
    0.09
    Negative Logits
    iated
    -0.79
    ategory
    -0.74
    itions
    -0.73
    umbn
    -0.73
    romy
    -0.73
    ris
    -0.71
    ornia
    -0.71
    rox
    -0.70
    iator
    -0.70
    uchin
    -0.69
    POSITIVE LOGITS
     versa
    0.76
    ordinary
    0.74
    wear
    0.72
    pants
    0.70
    TRY
    0.68
    borough
    0.67
    warm
    0.67
    bum
    0.66
     beware
    0.65
    stakes
    0.64
    Activations Density 1.592%

    No Known Activations