© 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. 9787
    Prev
    Next
    INDEX
    Explanations

    identifiable molecular markers and activity related to cellular processes and signaling pathways

    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
    111
    +0.63
    5.7%
    156
    +0.51
    4.6%
    25
    +0.12
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.63
    0.89
    156
    +0.51
    0.63
    71
    +0.12
    0.64
    Negative Logits
    ¿½
    -1.52
    ¿
    -1.42
    Ł
    -1.37
    ®
    -1.33
    ½
    -1.29
     stealth
    -1.29
    Ĥ
    -1.28
    ¶
    -1.28
     forg
    -1.27
    ¬
    -1.27
    POSITIVE LOGITS
    rosis
    1.47
     Cyt
    1.46
     cytos
    1.40
     concentration
    1.40
    ullary
    1.39
     Experiments
    1.34
     Clinical
    1.27
     concentrations
    1.25
     Fields
    1.25
    rox
    1.24
    Activations Density 1.681%

    No Known Activations