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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 34787
    Prev
    Next
    INDEX
    Explanations

    phrases related to confusion or uncertain situations

    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
    718
    +0.12
    0.6%
    596
    +0.11
    0.6%
    568
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    568
    +0.12
    0.07
    326
    +0.11
    0.19
    288
    +0.10
    0.18
    Negative Logits
     cynicism
    -0.65
     Imran
    -0.57
    vin
    -0.55
     territ
    -0.55
    ĪĴ
    -0.54
     tint
    -0.54
    xon
    -0.54
     vacuum
    -0.54
    nan
    -0.53
    Offic
    -0.53
    POSITIVE LOGITS
    erella
    0.95
    ernaut
    0.76
    erers
    0.74
    erer
    0.73
    endor
    0.70
    enegger
    0.69
    ilton
    0.68
    iest
    0.67
    engers
    0.67
    astic
    0.66
    Activations Density 7.119%

    No Known Activations