© 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. 23960
    Prev
    Next
    INDEX
    Explanations

    character representations in various formats

    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
    269
    +0.14
    0.8%
    108
    +0.13
    0.7%
    254
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.14
    0.03
    108
    +0.13
    0.03
    254
    +0.12
    0.03
    Negative Logits
     same
    -1.58
    ³
    -1.56
    hores
    -1.46
     site
    -1.45
     happening
    -1.44
     entire
    -1.40
    junction
    -1.40
    ype
    -1.39
    soever
    -1.36
    EV
    -1.36
    POSITIVE LOGITS
    acters
    2.50
    lier
    1.87
    alties
    1.85
    coal
    1.82
    mina
    1.81
    liest
    1.77
    nel
    1.76
    vie
    1.74
    rette
    1.70
    ified
    1.67
    Activations Density 0.073%

    No Known Activations