© 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. 29038
    Prev
    Next
    INDEX
    Explanations

    significant events related to notable dates and occurrences

    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
    23
    +0.17
    1.0%
    447
    +0.14
    0.8%
    408
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.17
    0.10
    447
    +0.14
    0.06
    373
    +0.12
    0.06
    Negative Logits
    ¹
    -2.71
    ī
    -2.68
    ĨĴ
    -2.61
    ±
    -2.58
    ½
    -2.56
    İ
    -2.53
    Ł
    -2.52
    »
    -2.34
    ¾
    -2.33
    ¬
    -2.32
    POSITIVE LOGITS
     where
    1.89
    acetate
    1.54
     terminus
    1.53
     Federation
    1.46
     far
    1.38
     dyst
    1.37
     colony
    1.37
     Branch
    1.32
    between
    1.32
     population
    1.30
    Activations Density 1.823%

    No Known Activations