© 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. 24970
    Prev
    Next
    INDEX
    Explanations

    thoughts or reflections expressed in the text

    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
    478
    +0.11
    0.6%
    459
    +0.11
    0.6%
    17
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.11
    0.04
    13
    +0.11
    0.04
    31
    +0.11
    0.04
    Negative Logits
    »¿
    -3.46
    ¨
    -3.25
    °
    -3.11
    ľĵ
    -3.10
    ©
    -3.06
    ¶
    -3.02
    ¢
    -3.02
    ¦
    -3.00
    ¸
    -2.98
    ¤
    -2.95
    POSITIVE LOGITS
     stratification
    1.69
     gon
    1.49
     exploitation
    1.44
     adaptation
    1.41
     entire
    1.40
     insult
    1.38
     taxonomic
    1.36
     Brazilian
    1.36
     actin
    1.35
     locals
    1.35
    Activations Density 0.015%

    No Known Activations