© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 32233
    Prev
    Next
    INDEX
    Explanations

    URLs or web links in the text

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    369
    +0.16
    0.9%
    478
    +0.14
    0.8%
    219
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    491
    +0.16
    0.03
    215
    +0.14
    0.03
    219
    +0.12
    0.02
    Negative Logits
    apine
    -2.03
    arily
    -1.82
    ively
    -1.76
    ymp
    -1.71
    inib
    -1.70
    ality
    -1.58
    iveness
    -1.56
    elves
    -1.51
    enix
    -1.49
    imer
    -1.47
    POSITIVE LOGITS
    ://
    3.46
    ³
    2.97
    ¡
    2.78
    ¿½
    2.74
    ¦
    2.56
    ©
    2.53
    ´
    2.48
    «
    2.48
    ¸
    2.47
    ĨĴ
    2.45
    Activations Density 0.065%

    No Known Activations