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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29617
    Prev
    Next
    INDEX
    Explanations

    references to the term "Salmon" and associated variations in content

    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
    369
    +0.17
    1.0%
    224
    +0.15
    0.9%
    203
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.17
    0.02
    503
    +0.15
    0.02
    86
    +0.11
    0.02
    Negative Logits
    rapeut
    -1.90
    oses
    -1.49
    ologically
    -1.48
    ferentially
    -1.44
     alia
    -1.42
    essage
    -1.37
     suppose
    -1.34
     characterised
    -1.34
     sectional
    -1.34
     accompl
    -1.33
    POSITIVE LOGITS
    vation
    2.14
    monella
    2.02
    nor
    1.67
    mond
    1.64
    iment
    1.63
    gue
    1.63
    vin
    1.61
    ved
    1.60
    ier
    1.59
    witz
    1.57
    Activations Density 0.069%

    No Known Activations