© 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. 30122
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions involving testimony or statements

    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
    369
    +0.14
    0.8%
    234
    +0.14
    0.8%
    484
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.14
    0.06
    352
    +0.14
    0.12
    410
    +0.13
    0.11
    Negative Logits
    anges
    -1.71
    rael
    -1.64
     Testament
    -1.61
    igious
    -1.55
    !(
    -1.49
    ű
    -1.49
    nament
    -1.48
    irth
    -1.40
    igraphy
    -1.32
    chat
    -1.30
    POSITIVE LOGITS
    2.07
    <|outofrange|>
    2.07
    ↵↵
    2.07
    2.07
    2.07
    ↵
    2.07
    2.07
    ↵↵
    2.07
    ↵
    2.07
    ↵
    2.07
    Activations Density 3.742%

    No Known Activations