© 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. 7434
    Prev
    Next
    INDEX
    Explanations

    bibliographic information within text

    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
    707
    +0.16
    0.6%
    42
    +0.12
    0.5%
    590
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.07
    409
    +0.12
    0.04
    707
    +0.11
    0.04
    Negative Logits
    lasting
    -0.89
    posed
    -0.87
    rooms
    -0.87
    lace
    -0.86
    boarding
    -0.85
    olves
    -0.84
    lynn
    -0.84
    bread
    -0.82
    mer
    -0.82
    dream
    -0.82
    POSITIVE LOGITS
    ibli
    1.39
    ographical
    1.24
    ographies
    1.17
    ophile
    1.16
    ibliography
    1.10
    DragonMagazine
    1.01
    ographic
    1.00
    ographically
    0.97
    ography
    0.92
    othe
    0.92
    Activations Density 0.504%

    No Known Activations