© 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. 29895
    Prev
    Next
    INDEX
    Explanations

    expressions related to conflict or authority

    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
    156
    +0.32
    1.8%
    88
    +0.14
    0.8%
    369
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.32
    0.26
    129
    +0.14
    -0.01
    406
    +0.10
    0.12
    Negative Logits
     */,
    -1.73
     Pradesh
    -1.61
    ")]
    -1.58
    strom
    -1.58
    consin
    -1.54
    "),
    -1.48
    uary
    -1.45
    aceae
    -1.40
     );
    -1.40
    printStackTrace
    -1.39
    POSITIVE LOGITS
    4.12
    4.12
    ↵↵
    4.12
    ↵  Âł
    4.12
    <|outofrange|>
    4.12
    4.12
    4.12
    ↵
    4.12
    4.12
    4.12
    Activations Density 9.896%

    No Known Activations