© 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 EvalsExportsAPI 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. 6973
    Prev
    Next
    INDEX
    Explanations

    words related to physical structures, specifically bridges

    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
    484
    +0.20
    0.7%
    526
    +0.17
    0.6%
    288
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.09
    325
    +0.17
    0.06
    484
    +0.16
    0.06
    Negative Logits
    ITH
    -0.95
    arily
    -0.94
    phis
    -0.89
    nesota
    -0.88
    eal
    -0.88
     STATES
    -0.87
    ean
    -0.87
    DERR
    -0.86
    isite
    -0.83
    ::::::::
    -0.83
    POSITIVE LOGITS
    port
    1.29
    yard
    1.21
    rupt
    1.05
    berry
    1.01
    bridge
    0.99
    ModLoader
    0.99
    roads
    0.98
    hole
    0.95
    chairs
    0.95
    strings
    0.94
    Activations Density 1.127%

    No Known Activations