© 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. 10261
    Prev
    Next
    INDEX
    Explanations

    specific entities or names mentioned in articles, such as authors, book titles, or organizations

    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
    739
    +0.17
    0.6%
    393
    +0.16
    0.6%
    368
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    97
    +0.17
    0.05
    703
    +0.16
    0.07
    126
    +0.13
    0.05
    Negative Logits
    cloth
    -1.04
    DERR
    -1.00
    umerable
    -0.95
    theless
    -0.88
    riber
    -0.87
    atel
    -0.84
    acters
    -0.83
    Redd
    -0.82
    daq
    -0.82
    bucks
    -0.81
    POSITIVE LOGITS
     Strategies
    1.30
     Contemporary
    1.23
     Everyday
    1.13
     Built
    1.10
     Evidence
    1.10
     Difference
    1.10
     Victims
    1.08
     Culture
    1.08
     Influence
    1.07
     Depend
    1.07
    Activations Density 2.139%

    No Known Activations