© 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. 10379
    Prev
    Next
    INDEX
    Explanations

    file pathways and code snippets related to library functions

    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
    503
    +0.17
    0.5%
    251
    +0.15
    0.5%
    571
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.11
    288
    +0.15
    0.12
    26
    +0.15
    0.08
    Negative Logits
     Resurrection
    -1.10
     boarding
    -1.10
    izational
    -1.01
    ister
    -0.99
     Undead
    -0.98
    ively
    -0.95
    terday
    -0.93
     Oaks
    -0.93
    velength
    -0.91
     Lauder
    -0.91
    POSITIVE LOGITS
    bing
    1.70
    bler
    1.67
    TeX
    1.66
    bers
    1.53
    rium
    1.52
    rious
    1.50
    bles
    1.48
    bed
    1.48
    riel
    1.46
    bons
    1.45
    Activations Density 2.264%

    No Known Activations