© 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 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. 33736
    Prev
    Next
    INDEX
    Explanations

    names of candies

    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
    288
    +0.13
    0.7%
    447
    +0.11
    0.6%
    326
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.20
    326
    +0.11
    0.17
    464
    +0.10
    0.08
    Negative Logits
    phrine
    -0.63
    chron
    -0.63
    iets
    -0.60
    yon
    -0.57
    productive
    -0.56
     plur
    -0.56
     Luxem
    -0.55
    shire
    -0.55
    lihood
    -0.54
     Peoples
    -0.53
    POSITIVE LOGITS
     cane
    0.95
     candy
    0.86
    strip
    0.85
    mallow
    0.84
    bucks
    0.81
     gum
    0.75
     wra
    0.75
    weet
    0.75
    corn
    0.74
    pole
    0.73
    Activations Density 5.060%

    No Known Activations