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. 2-RES-SM
    6. 29501
    Prev
    Next
    INDEX
    Explanations

    references to institutions, organizations, and government entities related to health and environmental policies

    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
    285
    +0.16
    0.9%
    271
    +0.14
    0.8%
    181
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.16
    0.08
    181
    +0.14
    0.07
    271
    +0.13
    0.00
    Negative Logits
    ľĵ
    -2.60
    ¯
    -2.54
    Īĺ
    -2.33
    ¿
    -2.23
    ½
    -2.14
    ª
    -2.13
    º
    -2.13
    ĨĴ
    -2.12
    ¶
    -2.08
    ı
    -2.05
    POSITIVE LOGITS
     Medal
    1.89
     Republic
    1.68
     Labor
    1.58
     Nations
    1.52
     Amend
    1.50
     Awards
    1.50
     Institutes
    1.49
     Award
    1.47
     Veterans
    1.45
    men
    1.45
    Activations Density 0.694%

    No Known Activations