© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11080
    Prev
    Next
    INDEX
    Explanations

    references to gaps or discrepancies in various contexts

    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
    182
    +0.14
    0.8%
    115
    +0.14
    0.8%
    473
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    115
    +0.14
    0.03
    182
    +0.14
    0.03
    413
    +0.12
    0.01
    Negative Logits
    ½
    -1.79
    ¦
    -1.77
    ¤
    -1.74
     behalf
    -1.67
     Parenthood
    -1.63
    ¸
    -1.61
     favour
    -1.60
     civilian
    -1.53
    ¿½
    -1.50
     favor
    -1.47
    POSITIVE LOGITS
    gap
    1.94
     junction
    1.90
     junctions
    1.78
    width
    1.73
    hole
    1.68
     depths
    1.66
     occlusion
    1.65
    neck
    1.60
    witz
    1.57
     separating
    1.56
    Activations Density 0.357%

    No Known Activations