© 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. 30959
    Prev
    Next
    INDEX
    Explanations

    instances of the word "accused."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.15
    0.8%
    177
    +0.13
    0.8%
    190
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    190
    +0.15
    0.02
    177
    +0.13
    0.02
    343
    +0.12
    0.02
    Negative Logits
    aned
    -1.74
     explained
    -1.56
    ...](
    -1.52
     answer
    -1.51
     supposed
    -1.47
     assumed
    -1.43
     predicted
    -1.41
     presumed
    -1.35
     advice
    -1.34
     celebrated
    -1.34
    POSITIVE LOGITS
    ently
    1.68
    uelle
    1.66
    hift
    1.54
    hell
    1.48
    mium
    1.48
    opan
    1.48
    uet
    1.44
    estion
    1.42
    áĢ¸
    1.41
    trl
    1.40
    Activations Density 0.238%

    No Known Activations