© 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. 30871
    Prev
    Next
    INDEX
    Explanations

    references to lottery-related terms or jargon

    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
    211
    +0.14
    0.8%
    250
    +0.13
    0.7%
    111
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    264
    +0.14
    0.01
    480
    +0.13
    0.01
    211
    +0.12
    0.01
    Negative Logits
     forthcoming
    -1.80
     longer
    -1.78
     COP
    -1.55
     Trans
    -1.46
     Labor
    -1.39
     slightest
    -1.37
    ...?"
    -1.36
     shorter
    -1.35
     disputed
    -1.35
    +$
    -1.33
    POSITIVE LOGITS
    pot
    2.04
    igan
    2.03
    fruit
    2.02
    als
    2.00
    iewicz
    1.74
    doms
    1.73
    manship
    1.69
    starter
    1.68
    rabbit
    1.67
    aul
    1.66
    Activations Density 0.126%

    No Known Activations