© 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. 23779
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs or phrases that indicate purpose or intention

    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
    478
    +0.14
    0.8%
    69
    +0.12
    0.7%
    23
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.13
    156
    +0.12
    0.07
    271
    +0.12
    0.04
    Negative Logits
    "</
    -1.68
    )">
    -1.63
     alone
    -1.58
    hole
    -1.56
    ĩ
    -1.56
    ”)
    -1.50
    ”
    -1.48
    msgstr
    -1.48
    )</
    -1.48
    ario
    -1.47
    POSITIVE LOGITS
    ftware
    1.53
     various
    1.44
    othing
    1.38
     Dress
    1.37
    cknow
    1.36
     pray
    1.35
    plist
    1.32
    exclude
    1.31
    OURCES
    1.28
     equitable
    1.26
    Activations Density 0.657%

    No Known Activations