© 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. 31235
    Prev
    Next
    INDEX
    Explanations

    instances of the word "converting" and its variations, indicating a focus on transformation or change in context

    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
    376
    +0.21
    1.2%
    148
    +0.15
    0.9%
    445
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.21
    0.01
    444
    +0.15
    0.01
    126
    +0.13
    0.01
    Negative Logits
     Indies
    -1.56
    ringer
    -1.55
    dern
    -1.54
    doing
    -1.47
    tails
    -1.47
    *=
    -1.46
    continue
    -1.44
    olding
    -1.43
    bery
    -1.42
    down
    -1.41
    POSITIVE LOGITS
     versions
    1.70
     thereto
    1.69
     version
    1.54
    ulated
    1.53
     effect
    1.53
     tool
    1.53
     machine
    1.52
     prototype
    1.49
    plicate
    1.46
     formulas
    1.45
    Activations Density 0.005%

    No Known Activations