© 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. 24102
    Prev
    Next
    INDEX
    Explanations

    terms related to registration and licensing processes

    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
    +0.13
    0.7%
    126
    +0.12
    0.6%
    494
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.13
    0.02
    389
    +0.12
    0.03
    388
    +0.10
    0.02
    Negative Logits
    ¯
    -3.85
    ĨĴ
    -3.52
    Ļ
    -3.20
    ¤
    -3.12
    º
    -3.09
    Ķ
    -3.07
    ĸ
    -3.06
    ¡
    -3.02
    ł
    -2.98
    ĻĤ
    -2.97
    POSITIVE LOGITS
    holder
    2.23
    ership
    1.98
    holders
    1.89
    keeper
    1.87
    bie
    1.86
    ares
    1.82
     expires
    1.80
    tees
    1.77
    born
    1.70
    ielle
    1.67
    Activations Density 0.211%

    No Known Activations