© 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. 30993
    Prev
    Next
    INDEX
    Explanations

    phrases related to susceptibility or vulnerability to various conditions or events

    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
    2
    +0.11
    0.6%
    90
    +0.10
    0.6%
    148
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.11
    0.01
    231
    +0.10
    0.01
    102
    +0.10
    0.01
    Negative Logits
     anything
    -1.56
     slightest
    -1.43
    affe
    -1.37
     anyone
    -1.37
     č
    -1.36
     sweat
    -1.36
    ever
    -1.35
     wonders
    -1.34
     nothing
    -1.28
     War
    -1.26
    POSITIVE LOGITS
    ģ
    2.93
    ĻĤ
    2.74
    ĺ
    2.61
    Ģ
    2.53
    ĩ
    2.48
    ľĵ
    2.33
    ↵↵
    2.28
    ↵↵
    2.28
    <|outofrange|>
    2.28
    ↵
    2.28
    Activations Density 0.072%

    No Known Activations