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. 26950
    Prev
    Next
    INDEX
    Explanations

    phrases that mention a capital city or the term "capital."

    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
    71
    +0.14
    0.8%
    417
    +0.12
    0.7%
    224
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.14
    0.02
    417
    +0.12
    0.02
    91
    +0.11
    0.02
    Negative Logits
    ³
    -4.30
    ª
    -4.24
    Ĥ¬
    -4.21
    ĨĴ
    -4.04
    »¿
    -3.80
    §
    -3.76
    ¯
    -3.69
    Ī
    -3.68
    ¢
    -3.66
    IJ
    -3.66
    POSITIVE LOGITS
    umes
    1.85
    illery
    1.83
     expenditure
    1.83
    ization
    1.80
    isations
    1.72
    izations
    1.69
    games
    1.68
     maze
    1.68
    atures
    1.63
     markets
    1.61
    Activations Density 0.118%

    No Known Activations