© 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. 31253
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering, such as "Rankine cycle" and "working fluid", along with mathematical terms like "rank" and "value constructor"

    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
    679
    +0.10
    0.7%
    447
    +0.08
    0.6%
    16
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.06
    130
    +0.08
    0.03
    205
    +0.07
    0.07
    Negative Logits
     Ezek
    -0.52
    ogene
    -0.50
    pha
    -0.50
    opic
    -0.49
    milo
    -0.49
    vous
    -0.48
    reens
    -0.48
    orescence
    -0.47
    adeon
    -0.47
    urnal
    -0.46
    POSITIVE LOGITS
    ably
    0.61
    liness
    0.60
    nance
    0.60
    Rank
    0.58
    ings
    0.57
    ific
    0.57
    able
    0.57
    eters
    0.55
    irection
    0.53
    ership
    0.53
    Activations Density 7.006%

    No Known Activations