© 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. 11675
    Prev
    Next
    INDEX
    Explanations

    references to the word "keg"

    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
    420
    +0.10
    0.8%
    599
    +0.07
    0.5%
    515
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.04
    420
    +0.07
    0.05
    232
    +0.06
    0.04
    Negative Logits
    enegger
    -0.51
    Ùħ
    -0.43
    Downloadha
    -0.43
    naire
    -0.42
    PsyNetMessage
    -0.41
    olutions
    -0.41
    child
    -0.41
    western
    -0.39
    olution
    -0.39
    å¹
    -0.39
    POSITIVE LOGITS
    erk
    0.64
    jriwal
    0.54
    pler
    0.52
    eter
    0.50
    erker
    0.50
    cers
    0.46
    eway
    0.45
    perate
    0.45
    pperc
    0.45
    isher
    0.45
    Activations Density 0.399%

    No Known Activations