© 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. 25663
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "measuring."

    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
    488
    +0.13
    0.7%
    194
    +0.13
    0.7%
    8
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.13
    0.01
    178
    +0.13
    0.01
    293
    +0.13
    0.01
    Negative Logits
     blame
    -1.68
    raise
    -1.54
    lu
    -1.46
    pile
    -1.45
    iju
    -1.42
    ahead
    -1.42
     top
    -1.41
    CRO
    -1.40
     piss
    -1.40
     crunch
    -1.39
    POSITIVE LOGITS
    ®
    1.77
    ©
    1.65
    ŀ
    1.61
    ¯
    1.61
    ly
    1.58
    ¦
    1.57
    »
    1.56
    Ĵ
    1.55
    ords
    1.48
    hof
    1.47
    Activations Density 0.001%

    No Known Activations