© 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. 11269
    Prev
    Next
    INDEX
    Explanations

    religious and spiritual themes, focusing on divine love, creation, and the interaction of the Holy Trinity

    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
    563
    +0.03
    0.4%
    185
    +0.03
    0.4%
    500
    +0.03
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.03
    -0.00
    701
    +0.03
    0.01
    436
    +0.03
    0.01
    Negative Logits
     WHERE
    -0.21
     ado
    -0.21
     Variant
    -0.20
    oooooooooooooooo
    -0.20
     vaccinations
    -0.20
     mathemat
    -0.20
     inval
    -0.20
    OOOO
    -0.20
     largeDownload
    -0.20
     helicop
    -0.20
    POSITIVE LOGITS
    enegger
    0.25
    iere
    0.24
    hower
    0.24
    avia
    0.21
    Ear
    0.21
    ulic
    0.21
    mare
    0.21
    eele
    0.21
    inois
    0.21
     "$:/
    0.21
    Activations Density 0.004%

    No Known Activations