© 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. 29018
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "Make 10."

    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
    135
    +0.17
    0.9%
    372
    +0.11
    0.6%
    213
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.17
    0.04
    60
    +0.11
    0.04
    243
    +0.11
    0.04
    Negative Logits
    ünd
    -1.95
    imum
    -1.64
    istors
    -1.64
    amen
    -1.59
    üller
    -1.59
    erk
    -1.59
    agt
    -1.55
    ün
    -1.53
    rue
    -1.52
    orms
    -1.52
    POSITIVE LOGITS
    ĵ
    3.13
    Ĥ¬
    3.11
    ģ
    3.02
    Ĩ
    2.74
    ĥ½
    2.73
    Īĺ
    2.68
    IJ
    2.64
    ¡
    2.63
    ¥
    2.58
    ¶
    2.56
    Activations Density 0.023%

    No Known Activations