© 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. 8356
    Prev
    Next
    INDEX
    Explanations

    statements or implications that are deemed evident or easily perceived

    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
    288
    +0.17
    0.6%
    707
    +0.14
    0.5%
    728
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.17
    0.09
    288
    +0.14
    0.09
    707
    +0.13
    0.06
    Negative Logits
    nan
    -1.26
    isol
    -1.06
    borg
    -1.03
    ingers
    -1.00
    rosse
    -0.98
    uden
    -0.97
    icum
    -0.93
    akin
    -0.91
    uese
    -0.91
    yss
    -0.91
    POSITIVE LOGITS
    iary
    1.50
     signs
    1.02
    itarian
    0.95
     departure
    0.94
     Signs
    0.92
    aneously
    0.91
     departures
    0.91
     deduction
    0.91
    LY
    0.90
     ($)
    0.89
    Activations Density 1.370%

    No Known Activations