© 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. 31151
    Prev
    Next
    INDEX
    Explanations

    expressions of visual attention or observation

    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
    23
    +0.16
    0.9%
    156
    +0.15
    0.8%
    466
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.16
    0.04
    148
    +0.15
    0.02
    432
    +0.14
    0.04
    Negative Logits
    ļ
    -2.27
    ¿½
    -2.26
    ĻĤ
    -2.13
    Ī
    -2.13
    ↵
    -2.10
    ↵
    -2.10
    <|outofrange|>
    -2.10
    -2.10
    ↵
    -2.10
    <|padding|>
    -2.10
    POSITIVE LOGITS
    acial
    1.66
    ype
    1.54
    ancell
    1.53
    uate
    1.52
    oven
    1.52
    disambiguation
    1.49
    atchewan
    1.46
    ))?
    1.45
     Scots
    1.40
     opposing
    1.38
    Activations Density 0.142%

    No Known Activations