© 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. 31642
    Prev
    Next
    INDEX
    Explanations

    information related to food preparation and cooking techniques, specifically focusing on ingredients and methods

    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
    497
    +0.06
    0.6%
    649
    +0.06
    0.5%
    326
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.06
    0.57
    447
    +0.06
    0.59
    64
    +0.06
    -0.20
    Negative Logits
     Panthers
    -0.34
    083
    -0.33
    anooga
    -0.33
     HL
    -0.33
     Fitzgerald
    -0.33
    FUL
    -0.32
    ļé
    -0.31
     drafts
    -0.31
    LET
    -0.31
    INTON
    -0.30
    POSITIVE LOGITS
    omething
    0.60
    cale
    0.56
    ome
    0.53
    creen
    0.52
    ystem
    0.51
    hip
    0.51
    omes
    0.49
    chool
    0.49
    OME
    0.47
    hift
    0.46
    Activations Density 12.311%

    No Known Activations