© 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. 36668
    Prev
    Next
    INDEX
    Explanations

    keywords related to enzymes, pathways, and biochemical functions, particularly focusing on proteins involved in signal transduction

    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
    496
    +0.03
    0.5%
    373
    +0.02
    0.4%
    156
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.03
    0.27
    640
    +0.02
    0.30
    107
    +0.02
    0.07
    Negative Logits
    NRS
    -0.20
     juggling
    -0.16
     humor
    -0.16
     jugg
    -0.16
    taker
    -0.15
     hitch
    -0.15
    ĨĴ
    -0.15
    \/\/
    -0.14
    enged
    -0.14
    ippi
    -0.14
    POSITIVE LOGITS
    ween
    0.23
    heimer
    0.21
    ajor
    0.21
    stocks
    0.21
    mere
    0.20
    emies
    0.20
    zyme
    0.19
    bur
    0.18
    ãĥĥãĥī
    0.18
    uity
    0.18
    Activations Density 14.537%

    No Known Activations