© 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. 10495
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of various topics and objects in a document, possibly relating to information or analysis

    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
    •Layer 6 UMAP region: e2e-recon outlier bottom right - e2e-recon

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.17
    0.9%
    640
    +0.14
    0.7%
    149
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.17
    0.37
    160
    +0.14
    0.28
    442
    +0.11
    0.22
    Negative Logits
    hire
    -0.64
    xon
    -0.57
     compelled
    -0.55
     overlook
    -0.55
     bananas
    -0.54
     mang
    -0.53
    ioned
    -0.50
    iuses
    -0.50
    onte
    -0.49
    kens
    -0.49
    POSITIVE LOGITS
    advertisement
    0.95
    SHARE
    0.67
    Contents
    0.63
     FAM
    0.63
    redients
    0.62
    Delivery
    0.61
    ":"/
    0.59
    Sold
    0.59
    division
    0.59
    Commission
    0.59
    Activations Density 5.398%

    No Known Activations