© 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. 28625
    Prev
    Next
    INDEX
    Explanations

    function declarations in the text

    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
    208
    +0.13
    0.7%
    193
    +0.12
    0.7%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.13
    0.06
    54
    +0.12
    0.05
    208
    +0.11
    0.05
    Negative Logits
    lic
    -1.77
    ling
    -1.73
    osa
    -1.72
    hores
    -1.69
    rein
    -1.61
    hei
    -1.55
    hot
    -1.50
    art
    -1.48
    whe
    -1.47
    olith
    -1.47
    POSITIVE LOGITS
    ľĵ
    3.93
    3.76
    3.76
    <|outofrange|>
    3.76
    č↵
    3.76
    ↵  ↵
    3.76
                  ↵
    3.76
    ↵↵
    3.76
    3.76
    ↵
    3.76
    Activations Density 0.371%

    No Known Activations