© 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. 30158
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and structures

    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
    172
    +0.11
    0.6%
    28
    +0.10
    0.5%
    383
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.11
    0.01
    422
    +0.10
    0.03
    419
    +0.09
    0.02
    Negative Logits
    atur
    -1.64
    rives
    -1.55
    aeda
    -1.50
    rolet
    -1.47
    imester
    -1.45
    hower
    -1.44
    ases
    -1.38
    år
    -1.35
    ikip
    -1.34
     halls
    -1.32
    POSITIVE LOGITS
    ĻĤ
    4.38
    ↵Č
    3.99
    ↵↵
    3.99
     ↵
    3.99
    3.99
      ↵
    3.99
    ↵↵
    3.99
    <|outofrange|>
    3.99
    ↵↵
    3.99
    <|outofrange|>
    3.99
    Activations Density 0.522%

    No Known Activations