© 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. 28547
    Prev
    Next
    INDEX
    Explanations

    the term "lantern"

    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
    441
    +0.12
    0.7%
    181
    +0.10
    0.6%
    16
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.12
    0.01
    181
    +0.10
    0.01
    16
    +0.10
    0.01
    Negative Logits
    Ŀ
    -2.37
    ľĵ
    -2.30
    Ĭ
    -2.23
    Ĥ
    -2.20
    ĥ
    -2.13
    ľ
    -2.09
    Ľ
    -2.05
    Īĺ
    -2.03
    ķ
    -2.02
    Į
    -1.96
    POSITIVE LOGITS
    anguage
    1.90
    enstein
    1.63
    uelle
    1.57
    loop
    1.54
    sizeof
    1.53
    caps
    1.47
    FW
    1.45
    ellar
    1.45
    bud
    1.44
    wealth
    1.42
    Activations Density 0.011%

    No Known Activations