© 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. 31167
    Prev
    Next
    INDEX
    Explanations

    programming code snippets and technical commands

    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
    205
    +0.06
    0.7%
    385
    +0.04
    0.5%
    447
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.06
    0.28
    267
    +0.04
    0.14
    739
    +0.04
    0.06
    Negative Logits
     Gree
    -0.29
     tallest
    -0.24
     furthe
    -0.24
     Luxem
    -0.23
     bearer
    -0.22
     exerc
    -0.22
    itiz
    -0.22
     bitters
    -0.22
     Bridgewater
    -0.22
     implanted
    -0.21
    POSITIVE LOGITS
    $$$$
    0.34
     Donation
    0.31
    GOP
    0.31
    EDIT
    0.30
     sudo
    0.28
    yip
    0.28
    cdn
    0.27
     cd
    0.27
     ls
    0.27
    maxwell
    0.26
    Activations Density 11.751%

    No Known Activations