© 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. 4-RES-SM
    11. 8935
    Prev
    Next
    INDEX
    Explanations

    references to "Nav" and its variations as part of a navigation or navigation-related context

    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
    348
    +0.14
    0.8%
    410
    +0.13
    0.7%
    9
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.14
    0.03
    329
    +0.13
    0.03
    9
    +0.12
    0.02
    Negative Logits
    keeping
    -2.07
    fulness
    -1.78
    fare
    -1.57
     rate
    -1.50
    ""
    -1.50
     expense
    -1.46
     """
    -1.40
    abine
    -1.40
    HECK
    -1.40
    mary
    -1.37
    POSITIVE LOGITS
    ¡
    4.96
    ª
    4.87
    ij
    4.85
    į
    4.84
    ŀ
    4.82
    ©
    4.73
    ¬
    4.70
    ĸ
    4.64
    ¾
    4.58
    ´
    4.57
    Activations Density 0.344%

    No Known Activations