© 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. 4-RES-SM
    11. 8674
    Prev
    Next
    INDEX
    Explanations

    quantifiers and expressions indicating quantity or degree

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    57
    +0.13
    0.7%
    193
    +0.12
    0.7%
    149
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.13
    0.05
    145
    +0.12
    0.05
    193
    +0.12
    0.06
    Negative Logits
    edly
    -1.63
    +$
    -1.59
    vdots
    -1.50
    ldots
    -1.44
     '\
    -1.39
    ){#
    -1.34
     puck
    -1.32
     trypsin
    -1.31
    emptyset
    -1.30
     midfielder
    -1.30
    POSITIVE LOGITS
     cases
    3.35
     contexts
    3.17
     respects
    2.98
     situations
    2.98
     circumstances
    2.74
     instances
    2.73
     jurisdictions
    2.53
     places
    2.47
     ways
    2.42
     regards
    2.39
    Activations Density 0.569%

    No Known Activations