© 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. 25346
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ham" 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
    369
    +0.21
    1.2%
    376
    +0.14
    0.8%
    410
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.21
    0.02
    20
    +0.14
    0.01
    211
    +0.13
    0.01
    Negative Logits
    ĥ
    -3.82
    ľ
    -3.69
    Ļ
    -3.66
    ĥ½
    -3.66
    ¢
    -3.65
    ľĵ
    -3.59
    Ŀ
    -3.56
    Ĩ
    -3.55
    ij
    -3.54
    ı
    -3.50
    POSITIVE LOGITS
    ilton
    1.70
    pton
    1.66
    pson
    1.66
    ilo
    1.59
    ford
    1.59
    leys
    1.57
    iga
    1.55
    mered
    1.54
    ibus
    1.50
    fest
    1.48
    Activations Density 0.009%

    No Known Activations