© 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. 35402
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms, such as specific materials, technologies, and medical conditions

    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
    447
    +0.28
    1.2%
    608
    +0.16
    0.7%
    393
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.28
    0.28
    393
    +0.16
    0.30
    362
    +0.15
    0.19
    Negative Logits
    ense
    -0.87
    lyak
    -0.84
    hyde
    -0.81
    faced
    -0.80
    winter
    -0.77
    claimed
    -0.74
    é¾įåĸļ士
    -0.74
    quote
    -0.73
    intosh
    -0.73
    icipated
    -0.73
    POSITIVE LOGITS
     afar
    1.12
     kindergarten
    0.81
     infancy
    0.73
     cradle
    0.72
     childhood
    0.69
     toddlers
    0.69
     scratch
    0.67
     preschool
    0.66
     bench
    0.66
     asteroids
    0.65
    Activations Density 12.859%

    No Known Activations