© 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. 31234
    Prev
    Next
    INDEX
    Explanations

    references to individuals in positions of authority or leadership roles

    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
    156
    +0.13
    0.7%
    38
    +0.13
    0.7%
    450
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.13
    0.03
    38
    +0.13
    0.02
    184
    +0.13
    0.02
    Negative Logits
     copyrighted
    -1.69
     DISTRICT
    -1.56
    >';
    -1.55
    rives
    -1.43
    OOGLE
    -1.39
    rived
    -1.37
    orence
    -1.36
    ended
    -1.35
    ayed
    -1.34
     borders
    -1.34
    POSITIVE LOGITS
    doms
    2.34
    ership
    1.95
    dom
    1.91
    piece
    1.85
    orphism
    1.80
     roles
    1.73
    pin
    1.70
    ship
    1.66
    boards
    1.65
     negot
    1.61
    Activations Density 0.227%

    No Known Activations