© 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. 2-RES-SM
    11. 32159
    Prev
    Next
    INDEX
    Explanations

    words related to chemical compounds and their classifications

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    419
    +0.27
    1.6%
    271
    +0.15
    0.9%
    391
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.27
    0.12
    391
    +0.15
    0.09
    86
    +0.14
    0.09
    Negative Logits
    ĻĤ
    -1.63
    Ī
    -1.56
    extend
    -1.50
    bsite
    -1.43
    ļ
    -1.37
     sake
    -1.29
     inclus
    -1.28
    icolor
    -1.27
    afe
    -1.27
     solutions
    -1.27
    POSITIVE LOGITS
    oto
    1.64
    ello
    1.63
    oxide
    1.54
    erie
    1.54
    gon
    1.52
    idone
    1.52
    nr
    1.47
    ὶ
    1.47
    hess
    1.43
    entes
    1.43
    Activations Density 1.316%

    No Known Activations