© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 28111
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "Questions" in various contexts

    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
    474
    +0.18
    1.1%
    376
    +0.14
    0.8%
    488
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.18
    0.01
    192
    +0.14
    0.01
    33
    +0.12
    0.01
    Negative Logits
    acetic
    -1.72
    lying
    -1.67
    mun
    -1.67
     chains
    -1.64
     APPEALS
    -1.50
    acy
    -1.50
     protective
    -1.47
    omorphisms
    -1.45
    acetate
    -1.44
    ometry
    -1.42
    POSITIVE LOGITS
    ¢
    1.88
    £
    1.86
    ¾
    1.82
    uelle
    1.77
    uet
    1.76
    cript
    1.70
    ļ
    1.68
    ²
    1.68
    ¥
    1.67
    Ĥ
    1.63
    Activations Density 0.011%

    No Known Activations