© 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. 1-RES-SM
    11. 25172
    Prev
    Next
    INDEX
    Explanations

    affirmative statements regarding the functionality or status of products or services

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    243
    +0.14
    0.8%
    419
    +0.14
    0.8%
    408
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.14
    0.10
    419
    +0.14
    0.06
    243
    +0.11
    0.08
    Negative Logits
    mond
    -1.61
    velopment
    -1.59
    hurst
    -1.53
     voices
    -1.50
    ument
    -1.49
    wick
    -1.49
    zona
    -1.47
     street
    -1.47
     chairs
    -1.45
     determinations
    -1.42
    POSITIVE LOGITS
     myself
    1.69
     ];
    1.52
    '];
    1.48
    plist
    1.46
    Override
    1.46
    isher
    1.45
    ';
    1.41
     );
    1.41
    ends
    1.40
    Sync
    1.39
    Activations Density 1.985%

    No Known Activations