© 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. 10568
    Prev
    Next
    INDEX
    Explanations

    references to drawing or sketching, especially in relation to artistic work

    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
    167
    +0.20
    0.8%
    726
    +0.15
    0.6%
    438
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.20
    0.03
    288
    +0.15
    0.04
    167
    +0.15
    0.01
    Negative Logits
    rogens
    -1.07
    adiator
    -0.87
    undai
    -0.85
    Ïī
    -0.84
    answered
    -0.82
    judicial
    -0.81
    inion
    -0.80
     rinse
    -0.80
     iod
    -0.79
     bom
    -0.77
    POSITIVE LOGITS
    eers
    1.29
    BOOK
    1.15
     Sketch
    1.15
     sketches
    1.08
    book
    1.07
     sketch
    1.07
    izable
    1.07
    enegger
    1.02
    eer
    1.01
    uring
    1.00
    Activations Density 0.269%

    No Known Activations