© 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. 12766
    Prev
    Next
    INDEX
    Explanations

    numerical values within text data

    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
    +0.10
    0.5%
    211
    +0.09
    0.5%
    17
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.23
    404
    +0.09
    0.10
    709
    +0.08
    0.12
    Negative Logits
     Greenwich
    -0.60
     Timeline
    -0.59
    Clock
    -0.58
     filibuster
    -0.55
     Pione
    -0.54
    EStream
    -0.54
     Proced
    -0.54
     Panthers
    -0.53
     CoC
    -0.53
     session
    -0.52
    POSITIVE LOGITS
    iveness
    0.73
    atives
    0.72
    iances
    0.71
    isms
    0.66
    urnal
    0.65
    ieri
    0.62
    alties
    0.61
    yles
    0.61
    aments
    0.59
    imation
    0.59
    Activations Density 11.793%

    No Known Activations