© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36154
    Prev
    Next
    INDEX
    Explanations

    instructions for DIY projects involving woodworking and painting

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    640
    +0.34
    1.9%
    447
    +0.33
    1.9%
    160
    +0.18
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.34
    0.33
    160
    +0.33
    0.26
    442
    +0.18
    0.18
    Negative Logits
     agre
    -0.72
     describ
    -0.71
     mathemat
    -0.69
     veter
    -0.67
     arri
    -0.66
     trump
    -0.65
     Mub
    -0.65
     retard
    -0.65
     evidenced
    -0.65
     treaty
    -0.63
    POSITIVE LOGITS
    Advertisements
    1.29
    ================================================================
    1.17
    --------------------------------------------------------
    1.16
    Conclusion
    1.16
    Reply
    1.09
    Other
    1.05
    Allows
    1.04
    Detailed
    1.04
    ********************************
    1.03
    ////////////////////////////////
    1.03
    Activations Density 7.798%

    No Known Activations