© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 37073
    Prev
    Next
    INDEX
    Explanations

    words related to attracting attention or interest, especially in the context of community events or products/services

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.25
    1.2%
    69
    +0.14
    0.7%
    183
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.25
    0.06
    69
    +0.14
    0.09
    393
    +0.14
    0.28
    Negative Logits
     procedure
    -0.64
     Oops
    -0.62
    jab
    -0.60
    chens
    -0.60
    hal
    -0.59
     surviving
    -0.57
    miah
    -0.56
     Adinida
    -0.56
     Norton
    -0.56
     Uz
    -0.55
    POSITIVE LOGITS
     attention
    0.83
    entious
    0.78
    GGGGGGGG
    0.77
     attract
    0.75
    kefeller
    0.74
     attracted
    0.74
    weights
    0.74
     attracts
    0.73
    dinand
    0.68
    tails
    0.68
    Activations Density 14.468%

    No Known Activations