Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26925
    Prev
    Next
    INDEX
    Explanations

    pronouns and expressions of possession

    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
    204
    +0.15
    0.8%
    155
    +0.14
    0.8%
    417
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.15
    0.07
    155
    +0.14
    0.06
    204
    +0.11
    0.06
    Negative Logits
    erad
    -1.70
    GREEK
    -1.59
     Disease
    -1.48
     silence
    -1.47
    glich
    -1.47
    translation
    -1.46
    packages
    -1.45
    itis
    -1.43
    hib
    -1.40
    itories
    -1.40
    POSITIVE LOGITS
     wrest
    1.54
    tech
    1.52
     happen
    1.50
     imagin
    1.43
     circle
    1.38
    iddy
    1.36
     hurry
    1.35
     gauge
    1.33
     dilig
    1.33
     chase
    1.32
    Activations Density 0.545%

    No Known Activations