© 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. 4-RES-SM
    11. 15377
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals, particularly those named Steve

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.22
    1.2%
    369
    +0.15
    0.9%
    410
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.22
    0.11
    369
    +0.15
    0.07
    177
    +0.14
    0.10
    Negative Logits
    ĥ½
    -2.96
    Ĥ¬
    -2.83
    Ĥ
    -2.81
    ¥
    -2.76
    °
    -2.72
    ĻĤ
    -2.71
    ²
    -2.67
    Ĺ
    -2.60
    ĨĴ
    -2.58
    Ķ
    -2.58
    POSITIVE LOGITS
     Smith
    2.27
     Mc
    2.23
     Snyder
    2.22
     Miller
    2.22
     Scott
    2.21
     McL
    2.19
     Mitchell
    2.18
     Anderson
    2.17
     Edwards
    2.17
     Cunningham
    2.15
    Activations Density 0.544%

    No Known Activations