© 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. 8722
    Prev
    Next
    INDEX
    Explanations

    scientific and technical information about chemicals, materials, and research procedures

    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
    639
    +0.03
    0.5%
    193
    +0.03
    0.5%
    595
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.03
    0.01
    214
    +0.03
    0.01
    534
    +0.03
    0.01
    Negative Logits
     CoC
    -0.20
     CPS
    -0.19
     punitive
    -0.18
    tein
    -0.18
     coalition
    -0.17
    ulative
    -0.17
    ategory
    -0.17
     portfolios
    -0.17
    atican
    -0.17
     traject
    -0.17
    POSITIVE LOGITS
    ook
    0.21
     Echoes
    0.19
    oola
    0.19
    Els
    0.19
    DonaldTrump
    0.19
    strip
    0.19
    ras
    0.19
    widget
    0.19
    Fear
    0.18
    rums
    0.18
    Activations Density 0.003%

    No Known Activations