© 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. 31117
    Prev
    Next
    INDEX
    Explanations

    expressions of happiness or positivity

    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
    112
    +0.15
    0.8%
    478
    +0.13
    0.7%
    258
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    112
    +0.15
    0.02
    140
    +0.13
    0.02
    278
    +0.12
    0.01
    Negative Logits
    Īĺ
    -2.45
    ´
    -2.27
    Ļª
    -2.22
    ¬
    -2.19
    ¢
    -2.14
    Ģ
    -2.13
    ħ
    -2.05
    Ł
    -2.04
    ®
    -2.02
    ·¸
    -1.95
    POSITIVE LOGITS
     climate
    1.45
    athe
    1.44
    perfect
    1.39
    acon
    1.36
    gmail
    1.35
     millenn
    1.34
    suits
    1.33
    bringing
    1.32
     teeth
    1.32
    tle
    1.32
    Activations Density 0.021%

    No Known Activations