© 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. 2-RES-SM
    11. 12761
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Pal" and related entities

    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
    369
    +0.14
    0.8%
    174
    +0.13
    0.7%
    466
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.14
    0.02
    374
    +0.13
    0.01
    187
    +0.12
    0.01
    Negative Logits
    legraph
    -1.57
     kidding
    -1.56
    resa
    -1.54
     entire
    -1.52
     chorus
    -1.50
    stant
    -1.49
    tig
    -1.47
     respective
    -1.46
     fact
    -1.43
    proving
    -1.41
    POSITIVE LOGITS
    ettes
    2.12
    estine
    1.90
    oon
    1.85
    azzo
    1.73
    adin
    1.72
    ī
    1.72
    ette
    1.71
    aces
    1.71
    wyn
    1.68
    asek
    1.63
    Activations Density 0.116%

    No Known Activations