© 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. 1-RES-SM
    11. 29636
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and their associated risks or effects

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.17
    0.9%
    171
    +0.12
    0.7%
    326
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.17
    0.01
    23
    +0.12
    0.06
    420
    +0.12
    0.01
    Negative Logits
    ĨĴ
    -2.23
    Ĭ
    -2.19
    ®
    -2.13
    Ģ
    -2.13
    ¬
    -2.13
    Ļª
    -1.96
    ¦
    -1.96
    Īĺ
    -1.94
    ĻĤ
    -1.92
    IJ
    -1.91
    POSITIVE LOGITS
     nowadays
    1.74
    abouts
    1.66
     families
    1.62
     consequence
    1.55
     ancestors
    1.48
    puted
    1.45
    ...)
    1.44
     conjug
    1.43
     suffering
    1.42
     conjugation
    1.42
    Activations Density 0.528%

    No Known Activations