© 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. 11747
    Prev
    Next
    INDEX
    Explanations

    terms related to financial policy, energy production, and government regulations

    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
    643
    +0.17
    0.6%
    270
    +0.15
    0.6%
    297
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.17
    0.10
    288
    +0.15
    0.13
    723
    +0.14
    0.08
    Negative Logits
    Äĩ
    -1.23
    issan
    -1.02
    thumbnails
    -0.99
    heric
    -0.95
     circulation
    -0.94
    olson
    -0.91
    Downloadha
    -0.90
    keyes
    -0.89
    together
    -0.89
    milo
    -0.86
    POSITIVE LOGITS
     Franch
    1.23
     Board
    1.19
     Initiative
    1.12
     Branch
    1.12
     Fund
    1.11
     Simulator
    1.09
     Manual
    1.09
     Partners
    1.08
     Bureau
    1.06
     Association
    1.05
    Activations Density 1.351%

    No Known Activations