© 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. 30480
    Prev
    Next
    INDEX
    Explanations

    references to the name "Calvin" and related mentions of "Scotch."

    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
    403
    +0.18
    1.0%
    369
    +0.17
    0.9%
    74
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.18
    0.02
    71
    +0.17
    0.01
    370
    +0.13
    0.01
    Negative Logits
    į
    -3.04
    ĨĴ
    -2.91
    ·¸
    -2.83
    ↵↵
    -2.69
    -2.69
    ↵    ↵
    -2.69
     ↵
    -2.69
    ↵↵
    -2.69
    -2.69
    -2.69
    POSITIVE LOGITS
    idian
    1.82
    IBLE
    1.64
    heimer
    1.63
     Klein
    1.58
    Einstein
    1.55
    IBILITY
    1.54
    gnu
    1.52
    ceral
    1.46
    ious
    1.45
     patented
    1.43
    Activations Density 0.294%

    No Known Activations