© 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. 25426
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantities or amounts

    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
    402
    +0.14
    0.8%
    409
    +0.12
    0.7%
    477
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.14
    0.05
    102
    +0.12
    0.04
    409
    +0.11
    0.04
    Negative Logits
    rait
    -1.89
    roll
    -1.78
    eler
    -1.71
    roc
    -1.61
    NER
    -1.59
    env
    -1.58
    ela
    -1.58
    ret
    -1.56
    pard
    -1.49
    ED
    -1.49
    POSITIVE LOGITS
    what
    1.91
    icals
    1.72
    how
    1.72
    amy
    1.70
     else
    1.54
    urate
    1.49
    lio
    1.49
    where
    1.47
     other
    1.46
     fancy
    1.42
    Activations Density 0.120%

    No Known Activations