© 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. 2-RES-SM
    11. 30860
    Prev
    Next
    INDEX
    Explanations

    phrases indicating authorship or attribution

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    478
    +0.20
    1.1%
    204
    +0.14
    0.8%
    407
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    88
    +0.20
    0.07
    108
    +0.14
    0.07
    407
    +0.12
    0.06
    Negative Logits
    theless
    -1.95
    heimer
    -1.57
    itious
    -1.56
    formation
    -1.48
    uality
    -1.48
    iness
    -1.38
    wort
    -1.38
    stress
    -1.37
    ingly
    -1.36
    ^](#
    -1.31
    POSITIVE LOGITS
    ľĵ
    2.37
    Į
    1.92
    emale
    1.85
    £
    1.83
    Ī
    1.79
    ĨĴ
    1.77
    Īĺ
    1.70
    Ļ
    1.69
     behalf
    1.67
    Ļª
    1.60
    Activations Density 0.261%

    No Known Activations