Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26838
    Prev
    Next
    INDEX
    Explanations

    references to licenses and governance in software documentation

    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
    303
    +0.15
    0.8%
    506
    +0.13
    0.8%
    76
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    76
    +0.15
    0.04
    305
    +0.13
    0.02
    464
    +0.13
    0.03
    Negative Logits
    ---|---|---
    -1.92
    ---|
    -1.86
    Users
    -1.49
    powers
    -1.42
    mid
    -1.41
    ICs
    -1.40
    |
    -1.40
    aneous
    -1.36
    Interval
    -1.36
    Performance
    -1.31
    POSITIVE LOGITS
     cov
    1.48
     guilty
    1.48
     biology
    1.43
     honor
    1.42
     jur
    1.42
    ?).
    1.40
    ibly
    1.40
     lectures
    1.39
    ));
    1.35
     memor
    1.34
    Activations Density 0.381%

    No Known Activations