© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7734
    Prev
    Next
    INDEX
    Explanations

    references to the name "Keith" in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    651
    +0.17
    0.7%
    679
    +0.17
    0.6%
    326
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.17
    288
    +0.17
    0.21
    651
    +0.14
    0.10
    Negative Logits
    ator
    -0.92
    ogy
    -0.90
    ny
    -0.89
    ated
    -0.88
    eral
    -0.86
    aries
    -0.83
    ition
    -0.83
    ists
    -0.82
    ģ
    -0.82
    ism
    -0.81
    POSITIVE LOGITS
    bourg
    1.01
    mare
    0.96
    mares
    0.95
    kson
    0.95
     Tanz
    0.93
    schild
    0.93
    mann
    0.92
    enegger
    0.91
    ynski
    0.89
    kens
    0.86
    Activations Density 3.355%

    No Known Activations