© 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. 29837
    Prev
    Next
    INDEX
    Explanations

    expressions of approval and disapproval

    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
    148
    +0.13
    0.7%
    376
    +0.12
    0.7%
    86
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.13
    0.02
    40
    +0.12
    0.01
    5
    +0.12
    0.01
    Negative Logits
    ical
    -1.67
    rely
    -1.66
    andez
    -1.61
    otle
    -1.55
    uality
    -1.52
    orget
    -1.50
    forth
    -1.49
    ALSE
    -1.48
    ANCE
    -1.47
    older
    -1.44
    POSITIVE LOGITS
     granted
    1.59
     awarded
    1.51
     shutter
    1.50
     loro
    1.48
     reproduce
    1.45
     feat
    1.43
     topp
    1.43
     win
    1.42
    =”
    1.41
    fileID
    1.40
    Activations Density 0.021%

    No Known Activations