© 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. 36020
    Prev
    Next
    INDEX
    Explanations

    names of individuals named Bryan and specific details related to them

    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
    649
    +0.13
    0.6%
    484
    +0.12
    0.6%
    343
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.22
    326
    +0.12
    0.22
    343
    +0.11
    0.10
    Negative Logits
    ively
    -0.93
    abulary
    -0.79
    iveness
    -0.67
    ende
    -0.67
    _>
    -0.65
    ives
    -0.65
    ivo
    -0.64
    othal
    -0.64
    isters
    -0.63
    ebin
    -0.62
    POSITIVE LOGITS
     Cran
    0.88
     Dani
    0.85
     Fuller
    0.85
     Bryan
    0.80
     Fischer
    0.80
     Adams
    0.77
    lin
    0.77
     Singer
    0.75
    bon
    0.71
     Koen
    0.71
    Activations Density 7.795%

    No Known Activations