© 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 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. 29361
    Prev
    Next
    INDEX
    Explanations

    instances of the word "own."

    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
    467
    +0.15
    0.9%
    316
    +0.11
    0.6%
    279
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    467
    +0.15
    0.02
    316
    +0.11
    0.01
    279
    +0.10
    0.02
    Negative Logits
     stay
    -1.52
    INCLUDING
    -1.48
     anyone
    -1.46
     prayed
    -1.45
    ?'
    -1.40
    've
    -1.34
     especially
    -1.34
     Stay
    -1.34
     thee
    -1.33
    ATE
    -1.32
    POSITIVE LOGITS
    ↵
    2.74
    č↵
    2.74
           ↵
    2.74
    <|outofrange|>
    2.74
    <|outofrange|>
    2.74
    <|outofrange|>
    2.74
             ↵
    2.74
    2.74
    ↵
    2.74
    2.74
    Activations Density 0.057%

    No Known Activations