© 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. 9041
    Prev
    Next
    INDEX
    Explanations

    statements related to consultation, discussion, and collaboration between individuals or groups

    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
    682
    +0.13
    0.5%
    28
    +0.12
    0.5%
    699
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.13
    0.06
    469
    +0.12
    0.06
    526
    +0.11
    -0.05
    Negative Logits
    Urban
    -0.78
    alg
    -0.77
    Young
    -0.73
     Folk
    -0.70
    iku
    -0.69
    Americ
    -0.69
    Deb
    -0.68
    gae
    -0.68
    NPR
    -0.68
    attr
    -0.67
    POSITIVE LOGITS
     inappropriately
    1.06
     unlawfully
    0.96
     illegally
    0.94
     prostitutes
    0.90
     Paddock
    0.87
     deliberately
    0.86
     improper
    0.86
     improperly
    0.85
     beforehand
    0.84
     inappropriate
    0.83
    Activations Density 6.262%

    No Known Activations