© 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. 25338
    Prev
    Next
    INDEX
    Explanations

    references to finality or conclusions

    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
    100
    +0.16
    0.9%
    362
    +0.12
    0.7%
    507
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    489
    +0.16
    0.03
    435
    +0.12
    0.03
    100
    +0.12
    0.03
    Negative Logits
    chitz
    -2.42
    lav
    -2.00
    forth
    -1.64
    fra
    -1.59
    ureus
    -1.55
    lder
    -1.55
    uchy
    -1.54
    aland
    -1.47
    dere
    -1.47
    per
    -1.47
    POSITIVE LOGITS
    izing
    2.01
    ising
    1.95
     tally
    1.86
    isations
    1.83
    ised
    1.83
    ized
    1.80
    izers
    1.69
    ists
    1.60
    isers
    1.57
     pronounce
    1.56
    Activations Density 0.074%

    No Known Activations