© 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. 28400
    Prev
    Next
    INDEX
    Explanations

    references to legal jurisdictions and case titles

    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
    435
    +0.12
    0.7%
    6
    +0.12
    0.7%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.12
    0.03
    71
    +0.12
    0.03
    272
    +0.11
    0.02
    Negative Logits
    [@
    -1.72
     ^[@
    -1.68
    former
    -1.60
    when
    -1.57
     [@
    -1.51
     drills
    -1.45
    through
    -1.43
     during
    -1.43
    mith
    -1.42
     torch
    -1.37
    POSITIVE LOGITS
    ´
    2.73
    ĻĤ
    2.67
    Ļª
    2.58
    Ŀ
    2.42
    ĥ½
    2.36
    ·
    2.31
    º
    2.27
    ¸
    2.24
    ĸ´
    2.24
    Ļ
    2.15
    Activations Density 0.181%

    No Known Activations