© 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. 36974
    Prev
    Next
    INDEX
    Explanations

    text related to revisions, changes, and modifications

    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
    447
    +0.08
    0.7%
    195
    +0.07
    0.6%
    450
    +0.07
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.08
    0.18
    450
    +0.07
    0.07
    195
    +0.07
    0.00
    Negative Logits
    ech
    -0.37
    asia
    -0.37
     Winged
    -0.36
     Mellon
    -0.34
    lehem
    -0.34
    pot
    -0.34
    gdala
    -0.34
    hesda
    -0.34
    esm
    -0.32
    Phones
    -0.31
    POSITIVE LOGITS
     revision
    0.49
     guiActiveUn
    0.45
    itized
    0.43
     revisions
    0.39
     Revision
    0.37
    dated
    0.36
     retrospect
    0.35
    é»Ĵ
    0.35
    ist
    0.34
    reading
    0.34
    Activations Density 5.241%

    No Known Activations