© 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. 2744
    Prev
    Next
    INDEX
    Explanations

    mentions of the abbreviation "DK" or variations of it

    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
    578
    +0.12
    0.5%
    339
    +0.11
    0.5%
    569
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.05
    343
    +0.11
    0.04
    659
    +0.10
    0.05
    Negative Logits
    tics
    -0.70
     membr
    -0.65
    icity
    -0.65
    frequency
    -0.64
     servicing
    -0.63
     reminders
    -0.62
    atis
    -0.61
     showc
    -0.61
    ttle
    -0.61
     Instr
    -0.59
    POSITIVE LOGITS
    vier
    0.91
    DK
    0.89
    apest
    0.89
    regate
    0.86
    cius
    0.80
    loo
    0.78
    arger
    0.76
    wallet
    0.72
    lad
    0.72
    ratom
    0.72
    Activations Density 0.398%

    No Known Activations