© 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. 2-MLP-SM
    11. 22496
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and emotions

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    335
    +0.14
    0.8%
    285
    +0.12
    0.7%
    482
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.14
    0.20
    285
    +0.12
    0.15
    94
    +0.11
    0.13
    Negative Logits
     discovery
    -1.76
    ffected
    -1.50
    woke
    -1.47
     spontaneous
    -1.43
     static
    -1.42
    INCLUDING
    -1.42
     whole
    -1.41
    uric
    -1.40
     longer
    -1.40
    transformed
    -1.38
    POSITIVE LOGITS
    cie
    1.70
    ço
    1.61
    chet
    1.54
    pora
    1.53
    town
    1.51
    forum
    1.49
    arium
    1.47
    bucks
    1.45
     Olympics
    1.43
    quo
    1.41
    Activations Density 4.996%

    No Known Activations