© 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. Residuals
    9. 1-RES-SM
    11. 29926
    Prev
    Next
    INDEX
    Explanations

    occurrences of hashtags in text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.20
    1.1%
    478
    +0.14
    0.8%
    111
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.20
    0.04
    156
    +0.14
    0.03
    271
    +0.13
    0.01
    Negative Logits
    ushima
    -1.71
    à«ĩ
    -1.61
    ators
    -1.60
    isers
    -1.58
    inces
    -1.58
    ables
    -1.56
    ittal
    -1.53
    iti
    -1.51
    engers
    -1.50
    iera
    -1.50
    POSITIVE LOGITS
     hear
    1.56
     write
    1.46
     commit
    1.46
     sleep
    1.43
     prayer
    1.40
     Writing
    1.40
     insomnia
    1.40
     love
    1.38
     Poetry
    1.38
     preach
    1.38
    Activations Density 0.107%

    No Known Activations