© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25176
    Prev
    Next
    INDEX
    Explanations

    references to deserts or desert-like conditions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.20
    1.2%
    180
    +0.15
    0.9%
    192
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.20
    0.02
    192
    +0.15
    0.02
    319
    +0.13
    0.01
    Negative Logits
    ck
    -1.62
    lementary
    -1.59
     promise
    -1.47
    ppers
    -1.47
     peritoneal
    -1.43
    '));
    -1.43
    inher
    -1.41
    ção
    -1.36
    EVER
    -1.32
    Association
    -1.31
    POSITIVE LOGITS
    Ł
    1.90
    vä
    1.86
    itud
    1.70
    arium
    1.70
    ¥
    1.68
    ainties
    1.63
    ibo
    1.62
    ģ
    1.61
    vation
    1.61
    imeter
    1.61
    Activations Density 0.018%

    No Known Activations