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. 26941
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions, specifically sciatic nerve pain

    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
    92
    +0.14
    0.8%
    156
    +0.13
    0.8%
    30
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.14
    0.02
    30
    +0.13
    0.02
    488
    +0.13
    0.02
    Negative Logits
     awake
    -2.00
     exact
    -1.90
     formal
    -1.82
     precise
    -1.77
     pure
    -1.74
     successful
    -1.70
     urgent
    -1.67
     definitive
    -1.64
     fertile
    -1.63
     particular
    -1.63
    POSITIVE LOGITS
    ŀ
    2.39
    £
    2.29
    º
    2.27
    ĻĤ
    2.20
    ¢
    2.11
    °
    2.08
    ¥
    2.07
    ¾
    1.99
    ¬
    1.96
    ĸ
    1.95
    Activations Density 0.072%

    No Known Activations