© 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. 25212
    Prev
    Next
    INDEX
    Explanations

    references to sickness and illness

    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
    156
    +0.18
    1.1%
    148
    +0.13
    0.8%
    362
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.18
    0.02
    161
    +0.13
    0.02
    344
    +0.13
    0.02
    Negative Logits
    <!--
    -1.81
    aliana
    -1.68
    FORE
    -1.53
     unsuccessful
    -1.52
    zier
    -1.42
     successful
    -1.39
    ---|---
    -1.34
    ories
    -1.32
    mes
    -1.31
    <
    -1.27
    POSITIVE LOGITS
    itzer
    1.66
    ensen
    1.50
    GHz
    1.45
    ercase
    1.43
    gart
    1.43
    opan
    1.43
    stuff
    1.43
    bay
    1.41
    hurst
    1.40
    vre
    1.37
    Activations Density 0.194%

    No Known Activations