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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13967
    Prev
    Next
    INDEX
    Explanations

    verbs in various forms, especially focusing on different tenses and their usage in questions or assertions

    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
    44
    +0.12
    0.7%
    290
    +0.11
    0.6%
    411
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.12
    0.05
    83
    +0.11
    0.06
    290
    +0.09
    0.04
    Negative Logits
    į
    -4.20
    ª
    -4.00
    Ŀ
    -4.00
    ¸
    -3.95
    Ķ
    -3.95
    ¢
    -3.92
    ¨
    -3.89
    ĥ
    -3.87
    Ħ
    -3.79
    ¶
    -3.77
    POSITIVE LOGITS
     it
    2.98
     they
    2.85
     there
    2.57
     you
    2.46
     we
    2.40
     anyone
    2.17
     anybody
    2.06
     she
    2.04
     he
    1.97
     someone
    1.96
    Activations Density 0.356%

    No Known Activations