© 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. 8754
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and conditions related to licenses

    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
    78
    +0.25
    1.6%
    21
    +0.20
    1.3%
    391
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.25
    0.02
    14
    +0.20
    0.02
    371
    +0.11
    0.02
    Negative Logits
    Ļª
    -2.00
    »¿
    -1.96
    ĸ´
    -1.93
    -1.90
     ↵
    -1.90
    -1.90
    ↵
    -1.90
     ↵
    -1.90
    -1.90
    <|outofrange|>
    -1.90
    POSITIVE LOGITS
     without
    1.67
     WITHOUT
    1.49
    circum
    1.49
     contrary
    1.37
     circumstances
    1.36
     lacking
    1.36
    nez
    1.33
    '"
    1.33
    without
    1.32
     WARRANTIES
    1.29
    Activations Density 0.031%

    No Known Activations