© 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 Local
    9. 6-RES_SCL-AJT
    11. 36386
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "knot" in various 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
    537
    +0.08
    0.5%
    213
    +0.08
    0.5%
    706
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.08
    0.26
    288
    +0.08
    0.25
    151
    +0.07
    0.17
    Negative Logits
    baugh
    -0.59
    raved
    -0.58
    gow
    -0.57
    urger
    -0.55
    er
    -0.55
    don
    -0.54
    rador
    -0.53
    ablishment
    -0.53
    ered
    -0.52
    ogly
    -0.52
    POSITIVE LOGITS
    itton
    0.63
     weaving
    0.62
    ting
    0.59
    aido
    0.57
     Leilan
    0.55
     knots
    0.54
    hered
    0.54
     Typhoon
    0.54
     knot
    0.54
    apon
    0.53
    Activations Density 10.809%

    No Known Activations