© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 2953
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific product or technology, including mentions of specific product features and instructions

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    231
    +0.15
    0.5%
    575
    +0.14
    0.5%
    25
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.10
    326
    +0.14
    0.08
    659
    +0.14
    0.06
    Negative Logits
     noodles
    -0.90
    ATE
    -0.87
    ately
    -0.87
    amental
    -0.87
    holder
    -0.84
    lain
    -0.83
     Pwr
    -0.82
    lists
    -0.82
    press
    -0.81
    EXP
    -0.81
    POSITIVE LOGITS
    verse
    1.26
    itored
    1.17
    pez
    1.16
    umatic
    1.15
    ph
    1.12
    ppings
    1.12
    ilst
    1.04
    ordinary
    1.04
    ppers
    1.04
    оÐ
    1.03
    Activations Density 1.234%

    No Known Activations