© 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. 22656
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate risk factors, specifically related to health conditions

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    476
    +0.12
    0.7%
    430
    +0.12
    0.6%
    53
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.12
    0.03
    476
    +0.12
    0.04
    5
    +0.10
    0.02
    Negative Logits
    [@
    -1.69
    abouts
    -1.67
     supra
    -1.64
    osus
    -1.56
    Care
    -1.54
     ([@
    -1.54
    .[@
    -1.52
     âĢķ
    -1.50
    over
    -1.49
     ([
    -1.41
    POSITIVE LOGITS
    °
    1.66
    ĨĴ
    1.64
    į
    1.58
     inbox
    1.57
     compilation
    1.57
     delegation
    1.51
     arsenal
    1.51
     RPG
    1.50
     delegate
    1.48
     counterpart
    1.48
    Activations Density 0.242%

    No Known Activations