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. 11868
    Prev
    Next
    INDEX
    Explanations

    medical terms related to abdominal and thoracic conditions

    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
    156
    +0.21
    1.2%
    207
    +0.12
    0.7%
    443
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.21
    0.01
    443
    +0.12
    0.01
    148
    +0.12
    0.00
    Negative Logits
     yours
    -1.73
     why
    -1.61
     precious
    -1.57
     beautiful
    -1.49
    eting
    -1.49
     harmless
    -1.48
     fictional
    -1.48
     polite
    -1.47
     forgotten
    -1.47
     dormant
    -1.47
    POSITIVE LOGITS
    µ
    3.95
    Ĺ
    3.73
    Ľ
    3.58
    ³
    3.55
    ŀ
    3.53
    ¢
    3.51
    ħ
    3.51
    ·
    3.50
    ĻĤ
    3.43
    £
    3.42
    Activations Density 0.076%

    No Known Activations