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. 27628
    Prev
    Next
    INDEX
    Explanations

    mentions of infertility and related reproductive issues

    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
    +0.21
    1.2%
    189
    +0.14
    0.8%
    43
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.21
    0.01
    156
    +0.14
    0.01
    71
    +0.11
    0.01
    Negative Logits
     gay
    -1.75
     tear
    -1.51
    rolled
    -1.46
     queer
    -1.46
     że
    -1.43
    uffling
    -1.42
    rolling
    -1.40
    ¯
    -1.36
     cual
    -1.36
    ahu
    -1.36
    POSITIVE LOGITS
     sciences
    1.90
    "}](#
    1.76
    àµį
    1.59
    à±į
    1.56
     experiments
    1.46
     mysteries
    1.44
    arial
    1.44
     occasions
    1.42
     workshops
    1.39
    erals
    1.39
    Activations Density 0.020%

    No Known Activations