© 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. 24575
    Prev
    Next
    INDEX
    Explanations

    references to voting and elections

    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
    72
    +0.13
    0.7%
    292
    +0.10
    0.6%
    374
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    72
    +0.13
    0.03
    323
    +0.10
    0.03
    260
    +0.10
    0.03
    Negative Logits
    ·¸
    -3.61
    ľ
    -3.39
    ŀ
    -3.33
    ©
    -3.30
    ĥ½
    -3.26
    Ł
    -3.24
    ↵↵
    -3.20
     ↵
    -3.20
    ↵  Âł
    -3.20
    ↵
    -3.20
    POSITIVE LOGITS
     ballots
    1.87
     nominee
    1.80
     referendum
    1.77
    ga
    1.69
     booth
    1.67
    ctomy
    1.62
    ems
    1.59
     polls
    1.58
     elections
    1.58
    gens
    1.56
    Activations Density 0.170%

    No Known Activations