© 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. 35568
    Prev
    Next
    INDEX
    Explanations

    information related to ultraviolet light and its interactions with various materials and substances

    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
    336
    +0.12
    0.5%
    349
    +0.12
    0.5%
    311
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.22
    288
    +0.12
    0.22
    57
    +0.11
    0.09
    Negative Logits
    wright
    -0.95
    piece
    -0.87
    leon
    -0.84
    aign
    -0.84
    zeb
    -0.77
    hart
    -0.76
    asia
    -0.76
    enson
    -0.75
    itia
    -0.74
    stal
    -0.73
    POSITIVE LOGITS
    raviolet
    1.25
    velength
    1.06
     ultraviolet
    0.97
     wavelengths
    0.97
     radiation
    0.93
     rays
    0.93
     ozone
    0.84
     sensitivity
    0.79
     infrared
    0.77
     Discrimination
    0.76
    Activations Density 8.017%

    No Known Activations