© 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. 32744
    Prev
    Next
    INDEX
    Explanations

    the name "Dave" within a variety of contexts

    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
    447
    +0.21
    1.0%
    167
    +0.13
    0.6%
    659
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.21
    0.11
    326
    +0.13
    0.14
    167
    +0.12
    -0.01
    Negative Logits
    undai
    -0.79
    ĺħ
    -0.78
    sighted
    -0.69
     unrestricted
    -0.67
     Flavoring
    -0.62
     condem
    -0.62
    ¥ŀ
    -0.62
     satell
    -0.61
    attled
    -0.61
    oresc
    -0.60
    POSITIVE LOGITS
     Matthews
    0.88
    y
    0.85
     Melt
    0.80
    tail
    0.79
     Barry
    0.77
    roll
    0.74
    yton
    0.73
     Foley
    0.72
    ys
    0.71
    yers
    0.70
    Activations Density 3.869%

    No Known Activations