© 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. 28114
    Prev
    Next
    INDEX
    Explanations

    references to the term "Cathar."

    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
    389
    +0.13
    0.7%
    142
    +0.13
    0.7%
    410
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    142
    +0.13
    0.01
    0
    +0.13
    0.01
    389
    +0.13
    0.01
    Negative Logits
    Ļª
    -2.53
    <|outofrange|>
    -2.53
     ↵
    -2.53
    -2.53
    ↵
    -2.53
    ↵
    -2.53
    <|outofrange|>
    -2.53
    -2.53
    ↵
    -2.53
    ↵↵
    -2.53
    POSITIVE LOGITS
    unov
    1.82
    opan
    1.61
    leen
    1.61
    arman
    1.57
    art
    1.50
    istine
    1.49
    ató
    1.48
    âĤ¬
    1.46
    âĨĴ
    1.45
    UAL
    1.44
    Activations Density 0.439%

    No Known Activations