© 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. 3097
    Prev
    Next
    INDEX
    Explanations

    information related to names of politicians, political events, and legal matters

    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
    433
    +0.14
    0.5%
    361
    +0.13
    0.5%
    256
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.14
    0.03
    595
    +0.13
    0.07
    393
    +0.12
    0.17
    Negative Logits
    Í
    -0.93
     spo
    -0.81
    oret
    -0.79
     DRAG
    -0.75
    fg
    -0.75
     deductions
    -0.69
    /-
    -0.68
     Kop
    -0.68
     helic
    -0.68
    BOOK
    -0.67
    POSITIVE LOGITS
     respectively
    1.10
    etheless
    0.88
     contend
    0.79
    collect
    0.79
    exist
    0.77
    ould
    0.73
    installed
    0.72
    utonium
    0.71
    stellar
    0.71
    addon
    0.71
    Activations Density 4.198%

    No Known Activations