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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 25808
    Prev
    Next
    INDEX
    Explanations

    references to families 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
    156
    +0.19
    1.2%
    87
    +0.14
    0.9%
    362
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.19
    0.02
    87
    +0.14
    0.02
    330
    +0.13
    0.02
    Negative Logits
    -3.32
     ↵
    -3.32
    ↵
    -3.32
    ↵
    -3.32
    -3.32
    -3.32
    <|outofrange|>
    -3.32
    ↵
    -3.32
    -3.32
    ↵
    -3.32
    POSITIVE LOGITS
    ière
    1.77
    etable
    1.73
    cript
    1.68
    hell
    1.67
    erals
    1.65
     quarters
    1.57
    pective
    1.55
    table
    1.54
    amente
    1.52
    ystems
    1.50
    Activations Density 0.017%

    No Known Activations