© 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. 22416
    Prev
    Next
    INDEX
    Explanations

    negative health outcomes and conditions

    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
    156
    +0.22
    1.3%
    23
    +0.20
    1.1%
    92
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.22
    0.02
    92
    +0.20
    0.01
    460
    +0.14
    0.01
    Negative Logits
    º
    -2.42
    ĨĴ
    -2.33
    Ļª
    -2.12
    ·¸
    -2.04
    ¢
    -1.96
    ¥
    -1.93
    Ħ
    -1.86
    »¿
    -1.84
    ±
    -1.82
    Į
    -1.82
    POSITIVE LOGITS
     signs
    1.65
     centers
    1.55
     procession
    1.53
     tiny
    1.51
    ring
    1.49
     thro
    1.49
     cracks
    1.46
     shaft
    1.43
    going
    1.43
     tunnel
    1.40
    Activations Density 0.096%

    No Known Activations