© 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. 37196
    Prev
    Next
    INDEX
    Explanations

    gestures or actions made by characters in a text

    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
    68
    +0.07
    0.6%
    99
    +0.06
    0.6%
    508
    +0.06
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.07
    0.13
    68
    +0.06
    0.08
    314
    +0.06
    -0.04
    Negative Logits
     awa
    -0.31
    bery
    -0.31
     derog
    -0.30
     Kenyan
    -0.30
     insensitive
    -0.29
    ovember
    -0.29
    pei
    -0.28
     unsupported
    -0.28
    ModLoader
    -0.28
    beit
    -0.27
    POSITIVE LOGITS
    alez
    0.47
    eger
    0.45
    orious
    0.43
    inel
    0.42
    apo
    0.42
    ured
    0.40
    urized
    0.39
    ablishment
    0.39
    alt
    0.39
    ez
    0.39
    Activations Density 8.901%

    No Known Activations