© 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. 7340
    Prev
    Next
    INDEX
    Explanations

    phrases related to do-it-yourself (DIY) projects or instructions

    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
    343
    +0.06
    0.6%
    535
    +0.05
    0.5%
    92
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.06
    0.04
    652
    +0.05
    0.03
    343
    +0.05
    0.03
    Negative Logits
    REDACTED
    -0.40
    ł
    -0.33
    ORD
    -0.32
     confessions
    -0.31
     absence
    -0.31
     absent
    -0.31
     defect
    -0.31
     unsur
    -0.31
    ELL
    -0.30
    furt
    -0.30
    POSITIVE LOGITS
    akedown
    0.36
    glers
    0.35
    ggie
    0.34
     Astro
    0.34
     Diablo
    0.34
    merce
    0.34
    ageddon
    0.33
    oola
    0.33
     Devi
    0.33
     shenan
    0.33
    Activations Density 0.326%

    No Known Activations