© 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. 9039
    Prev
    Next
    INDEX
    Explanations

    information related to historical events and figures, including political movements, government actions, and notable individuals

    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
    393
    +0.16
    0.6%
    584
    +0.14
    0.5%
    657
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.16
    0.17
    447
    +0.14
    0.18
    64
    +0.12
    -0.09
    Negative Logits
    oler
    -0.94
    ertain
    -0.92
    hya
    -0.91
    elta
    -0.91
    ibaba
    -0.91
     ende
    -0.89
    raq
    -0.88
     accur
    -0.88
    bia
    -0.86
    icip
    -0.86
    POSITIVE LOGITS
     Richard
    1.18
     John
    1.14
     Stephen
    1.14
     Karl
    1.12
     Rob
    1.11
     Gerald
    1.09
     William
    1.07
     Christine
    1.06
     Robert
    1.06
     George
    1.06
    Activations Density 2.544%

    No Known Activations