© 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. 22527
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" in various contexts

    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
    259
    +0.20
    1.1%
    496
    +0.11
    0.6%
    280
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.20
    0.04
    496
    +0.11
    0.03
    259
    +0.10
    0.02
    Negative Logits
    ÂĴ
    -1.53
     Hours
    -1.46
     reasons
    -1.43
    gor
    -1.43
    bler
    -1.38
    ric
    -1.36
    he
    -1.33
    hest
    -1.32
     brute
    -1.32
    ara
    -1.31
    POSITIVE LOGITS
     towards
    1.78
     attention
    1.63
    ship
    1.52
     toward
    1.49
     differentiate
    1.45
    /-/
    1.39
    gment
    1.32
    FromString
    1.32
    izes
    1.31
     manic
    1.27
    Activations Density 0.511%

    No Known Activations