© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 13580
    Prev
    Next
    INDEX
    Explanations

    disclaimers related to professional advice and information accuracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    307
    +0.17
    0.9%
    79
    +0.14
    0.8%
    456
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    79
    +0.17
    0.15
    222
    +0.14
    0.07
    439
    +0.13
    0.09
    Negative Logits
    ĨĴ
    -2.12
    ij
    -2.07
    »
    -2.07
    Ļª
    -2.04
    Ŀ
    -1.97
    ļ
    -1.82
     boss
    -1.81
    ¯
    -1.79
    ķ
    -1.78
    ĩ
    -1.74
    POSITIVE LOGITS
     copyright
    2.85
     disclaim
    2.49
     COPYRIGHT
    2.37
     Licensed
    2.36
     DISCLAIM
    2.34
     copyrighted
    2.23
     Copyright
    2.22
     confidentiality
    2.21
     Terms
    2.17
     trademarks
    2.13
    Activations Density 2.763%

    No Known Activations