© 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. 31782
    Prev
    Next
    INDEX
    Explanations

    repeated mentions or references to the word "Par."

    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
    +0.16
    0.9%
    502
    +0.14
    0.8%
    463
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.16
    0.02
    391
    +0.14
    0.02
    30
    +0.12
    0.02
    Negative Logits
    ¢
    -3.09
    ĥ½
    -2.97
    ľĵ
    -2.76
    Ļ
    -2.73
    »
    -2.65
    ³
    -2.57
    Ń
    -2.55
    Ģ
    -2.51
    ¥
    -2.50
    ¡
    -2.41
    POSITIVE LOGITS
    cels
    2.12
    agraph
    2.04
    leys
    1.94
    ley
    1.76
    lee
    1.73
    anches
    1.65
    allel
    1.60
     sized
    1.59
    ibus
    1.53
     stamped
    1.52
    Activations Density 0.120%

    No Known Activations