© 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. 26396
    Prev
    Next
    INDEX
    Explanations

    attributes related to width and height measurements

    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
    217
    +0.14
    0.8%
    156
    +0.14
    0.8%
    269
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    245
    +0.14
    0.02
    269
    +0.14
    0.01
    506
    +0.13
    0.01
    Negative Logits
    ¿
    -2.39
    ¿½
    -2.37
    Ĥ
    -2.29
    ķ
    -2.28
    ĵ
    -2.23
    ĥ½
    -2.12
    ¸
    -2.01
    ·
    -1.99
    ±
    -1.95
    Īĺ
    -1.93
    POSITIVE LOGITS
    eno
    1.98
    quel
    1.75
    edo
    1.68
    ière
    1.66
    robe
    1.64
    enum
    1.63
    book
    1.63
     era
    1.63
    ened
    1.62
    sheet
    1.60
    Activations Density 0.028%

    No Known Activations