© 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. 23918
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of revealing or making information known

    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
    365
    +0.17
    1.0%
    493
    +0.13
    0.7%
    148
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    493
    +0.17
    0.01
    148
    +0.13
    0.01
    231
    +0.13
    0.01
    Negative Logits
    =”
    -1.81
    etica
    -1.61
    ace
    -1.59
    AML
    -1.58
    anks
    -1.56
    âĢ³
    -1.56
    akan
    -1.52
    bilt
    -1.52
    amycin
    -1.49
    !’
    -1.47
    POSITIVE LOGITS
    ª
    1.99
    °
    1.65
     mine
    1.63
    ulate
    1.60
    ĻĤ
    1.54
     invention
    1.50
     about
    1.49
    ²
    1.48
    having
    1.47
    ľ
    1.47
    Activations Density 0.052%

    No Known Activations