© 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. 25074
    Prev
    Next
    INDEX
    Explanations

    negative phrases or discussions surrounding cannabis regulations or implications

    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
    113
    +0.16
    0.9%
    128
    +0.13
    0.7%
    19
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.16
    0.45
    209
    +0.13
    0.29
    402
    +0.11
    0.26
    Negative Logits
     care
    -1.71
     misplaced
    -1.51
     common
    -1.51
    power
    -1.42
     mantle
    -1.39
    reserved
    -1.39
     committed
    -1.37
     ever
    -1.36
    umber
    -1.35
    cer
    -1.34
    POSITIVE LOGITS
    º
    4.33
    Ł
    4.11
    Ļ
    3.98
    ĸ
    3.95
    ķ
    3.89
    Īĺ
    3.86
    ĨĴ
    3.84
    ĥ½
    3.82
    ·¸
    3.81
    ĭ
    3.79
    Activations Density 1.588%

    No Known Activations