© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24113
    Prev
    Next
    INDEX
    Explanations

    references to the company Apple and its products

    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
    156
    +0.23
    1.3%
    369
    +0.17
    1.0%
    410
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.23
    0.03
    156
    +0.17
    0.02
    271
    +0.13
    0.01
    Negative Logits
    ĺ
    -3.27
    Ļª
    -2.90
    Ĥ¬
    -2.89
    ĥ½
    -2.83
    ĻĤ
    -2.75
    Ł
    -2.72
    ľ
    -2.69
    £
    -2.60
    ij
    -2.58
    ĭ
    -2.56
    POSITIVE LOGITS
    lectual
    1.95
    wood
    1.77
     reserves
    1.61
    ville
    1.56
    bles
    1.55
     logo
    1.55
    dom
    1.54
    oslav
    1.52
    doms
    1.50
    redit
    1.50
    Activations Density 0.214%

    No Known Activations