© 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. 30051
    Prev
    Next
    INDEX
    Explanations

    contextual references to mapping or configurations in various domains

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    230
    +0.15
    0.8%
    470
    +0.13
    0.7%
    15
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.15
    0.04
    156
    +0.13
    0.07
    392
    +0.13
    0.05
    Negative Logits
    fulness
    -1.67
     alleged
    -1.60
     completing
    -1.58
     washing
    -1.58
     checking
    -1.57
     approaching
    -1.55
     beating
    -1.54
     first
    -1.53
     attending
    -1.52
     receiving
    -1.50
    POSITIVE LOGITS
    ±
    2.60
    ¶
    2.52
    ¢
    2.44
    ĨĴ
    2.43
    ĸ
    2.42
    £
    2.39
    °
    2.39
    ¥
    2.37
    ¬
    2.30
    ¾
    2.28
    Activations Density 0.838%

    No Known Activations