© 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. 24488
    Prev
    Next
    INDEX
    Explanations

    references to basketball and its players

    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
    471
    +0.15
    0.9%
    156
    +0.14
    0.8%
    93
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.15
    0.03
    341
    +0.14
    0.03
    476
    +0.11
    0.03
    Negative Logits
     varying
    -1.60
     specifying
    -1.55
     ces
    -1.51
     request
    -1.49
     Privacy
    -1.49
     indefinite
    -1.48
    ago
    -1.47
    ·
    -1.46
     comma
    -1.45
     denote
    -1.43
    POSITIVE LOGITS
    makers
    2.14
    istan
    2.01
    ennis
    1.95
    ief
    1.90
    assets
    1.87
    maker
    1.76
     games
    1.67
    break
    1.62
    Foundation
    1.61
    raits
    1.59
    Activations Density 0.132%

    No Known Activations