© 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. 11543
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that involve a lot of punctuation and symbols

    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
    75
    +0.14
    0.5%
    683
    +0.14
    0.5%
    413
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.14
    0.09
    326
    +0.14
    0.14
    514
    +0.14
    0.06
    Negative Logits
     plur
    -1.00
     defect
    -0.85
    azeera
    -0.85
     bay
    -0.84
    clerosis
    -0.83
     migr
    -0.83
    worldly
    -0.83
    ativity
    -0.82
    ovych
    -0.82
     mysterious
    -0.81
    POSITIVE LOGITS
    agall
    1.13
    asus
    1.12
    itent
    1.09
    sylvania
    1.08
    ĵĺ
    1.07
    ciation
    1.06
    γ
    1.05
    lator
    1.03
    ongyang
    1.00
    ople
    0.97
    Activations Density 3.711%

    No Known Activations