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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26979
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of."

    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
    +0.17
    0.9%
    12
    +0.11
    0.6%
    412
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.17
    0.03
    18
    +0.11
    0.03
    12
    +0.11
    0.02
    Negative Logits
    ģ
    -2.34
    ©
    -2.22
    ī
    -2.22
    ¸
    -2.17
    ¼
    -2.00
    İ
    -1.98
    Ĵ
    -1.98
    ¡
    -1.98
    ĭ
    -1.97
    ¢
    -1.97
    POSITIVE LOGITS
    opes
    1.73
    clusions
    1.62
     strange
    1.54
     knots
    1.54
     years
    1.53
     weeks
    1.48
     Parenthood
    1.47
    cgi
    1.46
     silly
    1.46
    ittal
    1.45
    Activations Density 0.196%

    No Known Activations