© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 13937
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and names, specifically those associated with royalty

    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
    418
    +0.11
    0.6%
    288
    +0.10
    0.5%
    754
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.11
    0.04
    326
    +0.10
    0.21
    288
    +0.10
    0.20
    Negative Logits
    hma
    -0.81
    EStreamFrame
    -0.78
    enegger
    -0.76
    perse
    -0.73
    ãĤ¿
    -0.71
    INESS
    -0.71
    pelled
    -0.69
    SPONSORED
    -0.68
    cript
    -0.67
    pmwiki
    -0.66
    POSITIVE LOGITS
     Thatcher
    1.16
    aret
    0.91
     Margaret
    0.89
     Rodham
    0.79
     Keane
    0.72
    ricia
    0.69
     Downs
    0.67
    erest
    0.66
     Anne
    0.65
     Isabel
    0.65
    Activations Density 7.973%

    No Known Activations