© 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 Local
    9. 6-RES_SCL-AJT
    11. 31236
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases related to programming, code structure, and technical instructions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    87
    +0.32
    4.4%
    447
    +0.29
    4.1%
    64
    +0.22
    3.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.32
    -0.00
    64
    +0.29
    -0.13
    640
    +0.22
    0.23
    Negative Logits
    boro
    -0.21
    fol
    -0.19
    idge
    -0.18
    heid
    -0.17
    pine
    -0.17
    ierre
    -0.17
    LGBT
    -0.17
    ranch
    -0.17
    itamin
    -0.17
     Canad
    -0.17
    POSITIVE LOGITS
     Conclusion
    0.23
    ertodd
    0.20
    \/\/
    0.20
    Conclusion
    0.20
    âĸ¬
    0.19
    endum
    0.19
    ogether
    0.18
     Eisen
    0.18
    ¶
    0.18
     Fischer
    0.18
    Activations Density 3.868%

    No Known Activations