© 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. 25526
    Prev
    Next
    INDEX
    Explanations

    Java utility classes and their associated imports

    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
    438
    +0.13
    0.8%
    453
    +0.11
    0.6%
    189
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.13
    0.03
    453
    +0.11
    0.02
    54
    +0.11
    0.02
    Negative Logits
    aways
    -1.75
    away
    -1.60
    Else
    -1.49
    xit
    -1.46
    atri
    -1.41
     Else
    -1.40
    ori
    -1.40
    \[[@
    -1.37
     lest
    -1.36
    then
    -1.35
    POSITIVE LOGITS
    £
    2.50
    ¥
    1.90
    ¬
    1.84
    ĨĴ
    1.81
    ¢
    1.78
    ĻĤ
    1.75
    ¡
    1.73
    į
    1.71
    Īĺ
    1.67
    Ģ
    1.64
    Activations Density 0.083%

    No Known Activations