© 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. 1-RES-SM
    11. 24084
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods and commas

    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
    81
    +0.15
    0.8%
    282
    +0.12
    0.6%
    449
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    229
    +0.15
    0.01
    31
    +0.12
    0.02
    442
    +0.12
    0.02
    Negative Logits
    ®
    -2.40
    Ĵ
    -2.07
    ī
    -2.05
    ĨĴ
    -1.99
    İ
    -1.95
    Ģ
    -1.91
    ĵ
    -1.88
    ı
    -1.80
    Ļ
    -1.80
    ģ
    -1.79
    POSITIVE LOGITS
    pson
    1.58
    ulations
    1.52
    ker
    1.51
    chs
    1.44
    however
    1.43
     deficient
    1.42
     moreover
    1.42
    also
    1.40
     therefore
    1.40
    therefore
    1.38
    Activations Density 0.142%

    No Known Activations