© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12234
    Prev
    Next
    INDEX
    Explanations

    phrases related to law and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    25
    +0.25
    1.6%
    466
    +0.16
    1.0%
    397
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.25
    0.11
    308
    +0.16
    0.04
    466
    +0.13
    0.10
    Negative Logits
    į
    -1.37
    ī
    -1.32
    xymatrix
    -1.30
    ,[
    -1.30
    [,
    -1.27
    000001
    -1.26
    ª
    -1.23
    (:
    -1.23
    [^
    -1.21
    00001
    -1.20
    POSITIVE LOGITS
     the
    3.19
    the
    2.56
     THE
    2.09
     The
    1.65
    The
    1.57
    THE
    1.54
     their
    1.48
    autres
    1.47
    terest
    1.37
    tha
    1.31
    Activations Density 2.020%

    No Known Activations