© 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 Local
    9. 6-RES_SCL-AJT
    11. 37086
    Prev
    Next
    INDEX
    Explanations

    content with a variety of characters and language syntax

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    284
    +0.13
    0.7%
    447
    +0.12
    0.6%
    311
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.13
    0.19
    293
    +0.12
    0.19
    675
    +0.12
    0.19
    Negative Logits
    iage
    -0.76
    engers
    -0.69
    zee
    -0.67
     Hole
    -0.67
    itudinal
    -0.66
    zees
    -0.64
     Osw
    -0.64
    mares
    -0.63
    witz
    -0.62
     Lans
    -0.61
    POSITIVE LOGITS
    女
    1.04
    âĸijâĸij
    1.01
    entric
    0.94
    ption
    0.93
    actus
    0.84
    LECT
    0.82
    âĸij
    0.81
    VID
    0.79
    ij
    0.79
    æĪ¦
    0.78
    Activations Density 7.310%

    No Known Activations