© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26119
    Prev
    Next
    INDEX
    Explanations

    statistical values and comparisons regarding medical or scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.33
    1.9%
    369
    +0.12
    0.7%
    129
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.33
    0.08
    176
    +0.12
    0.07
    3
    +0.11
    0.05
    Negative Logits
    liga
    -1.89
    ibil
    -1.63
     NFC
    -1.59
     rece
    -1.58
     assist
    -1.56
    inux
    -1.53
    abil
    -1.52
     ment
    -1.52
    ibles
    -1.50
    naire
    -1.50
    POSITIVE LOGITS
     investigators
    2.11
     researchers
    2.06
    then
    1.99
     authors
    1.92
     conclusions
    1.75
    ↵↵
    1.67
    ↵
    1.67
    č↵č↵
    1.67
    1.67
     ↵
    1.67
    Activations Density 1.266%

    No Known Activations