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. 11554
    Prev
    Next
    INDEX
    Explanations

    terms related to influenza and its vaccines

    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
    177
    +0.14
    0.8%
    156
    +0.13
    0.7%
    314
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.14
    0.02
    386
    +0.13
    0.01
    67
    +0.13
    0.01
    Negative Logits
    hip
    -1.73
     dere
    -1.69
    wards
    -1.66
     où
    -1.60
    ward
    -1.55
     después
    -1.54
    hips
    -1.50
     why
    -1.47
     jeg
    -1.45
    rish
    -1.45
    POSITIVE LOGITS
    orescent
    1.84
    acious
    1.82
    ence
    1.77
    idity
    1.74
    ency
    1.69
    ishes
    1.67
    orescence
    1.65
    ência
    1.62
    sted
    1.60
    uer
    1.58
    Activations Density 0.136%

    No Known Activations