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. MLP Post
    5. 0-MLP-SM
    6. 27379
    Prev
    Next
    INDEX
    Explanations

    terms related to heart disease or cardiac conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    +0.28
    1.7%
    327
    +0.11
    0.7%
    443
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.28
    0.00
    327
    +0.11
    0.00
    184
    +0.11
    0.00
    Negative Logits
     cual
    -1.65
    uffling
    -1.50
    hes
    -1.45
     racist
    -1.43
    woke
    -1.38
    edes
    -1.35
    že
    -1.32
     click
    -1.32
     fois
    -1.32
    ção
    -1.31
    POSITIVE LOGITS
     emergencies
    1.64
     stems
    1.59
     regimes
    1.57
     (,
    1.46
     HV
    1.45
    break
    1.43
     infrastructure
    1.37
     irrigation
    1.37
     relies
    1.36
     originates
    1.34
    Activations Density 0.006%

    No Known Activations