© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 23823
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals or specific names related to incidents

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    260
    +0.15
    0.8%
    269
    +0.12
    0.7%
    354
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.15
    0.04
    334
    +0.12
    0.04
    386
    +0.11
    0.03
    Negative Logits
    Ł
    -3.20
    Ĥ
    -3.00
    ´
    -2.99
    Ĩ
    -2.91
    ¦
    -2.91
    ·¸
    -2.89
    Ķ
    -2.85
    ¿½
    -2.84
    Ĺ
    -2.75
    ĵ
    -2.71
    POSITIVE LOGITS
    ings
    1.73
    cz
    1.72
    ew
    1.69
    bek
    1.68
    emer
    1.66
    ingly
    1.63
    iah
    1.55
    alore
    1.55
    illas
    1.54
    nik
    1.51
    Activations Density 0.087%

    No Known Activations