© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10253
    Prev
    Next
    INDEX
    Explanations

    information related to sports, particularly football and specific player performance in preseason games

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.14
    0.5%
    16
    +0.14
    0.5%
    611
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.14
    0.05
    146
    +0.14
    0.05
    527
    +0.13
    0.04
    Negative Logits
    etsk
    -1.15
    arget
    -1.05
    rans
    -0.98
    akin
    -0.93
    riv
    -0.92
    terday
    -0.92
    olen
    -0.91
    hra
    -0.89
    itudinal
    -0.88
    perm
    -0.88
    POSITIVE LOGITS
    rules
    1.02
     Playoff
    0.98
     Writers
    0.95
     Federation
    0.94
     Handbook
    0.94
     Salary
    0.93
     rules
    0.92
     Crate
    0.90
     Accountability
    0.89
     Finder
    0.86
    Activations Density 0.394%

    No Known Activations