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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4619
    Prev
    Next
    INDEX
    Explanations

    recipes and cooking instructions for various dishes

    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
    +0.21
    1.0%
    683
    +0.11
    0.5%
    302
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.21
    0.29
    362
    +0.11
    0.16
    393
    +0.11
    0.29
    Negative Logits
    umerable
    -0.68
    rights
    -0.68
    iseum
    -0.68
    Kings
    -0.67
    banks
    -0.66
     Coliseum
    -0.66
    apego
    -0.66
    conference
    -0.65
     Halls
    -0.63
    Domain
    -0.63
    POSITIVE LOGITS
     dab
    0.95
     baking
    0.92
     teaspoons
    0.87
     tsp
    0.87
     teaspoon
    0.84
    poons
    0.78
     frost
    0.75
    bsp
    0.73
     pinch
    0.71
     cinnamon
    0.70
    Activations Density 12.449%

    No Known Activations