© 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. 25082
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation marks

    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
    190
    +0.13
    0.7%
    179
    +0.12
    0.7%
    396
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.13
    0.01
    23
    +0.12
    0.01
    440
    +0.12
    0.00
    Negative Logits
    ,\[
    -1.67
    ème
    -1.62
    eme
    -1.58
    ione
    -1.58
    nership
    -1.50
    tion
    -1.48
    ands
    -1.47
    emeter
    -1.47
    iverse
    -1.43
    .\[[@
    -1.42
    POSITIVE LOGITS
    ĥ½
    2.73
    °
    2.69
    <|outofrange|>
    2.65
    ↵↵
    2.65
    ↵
    2.65
    ↵
    2.65
    2.65
     ↵
    2.65
          ↵
    2.65
    2.65
    Activations Density 0.002%

    No Known Activations