© 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. 2-RES-SM
    11. 31288
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and statistics related to measurements or ratings

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    17
    +0.21
    1.2%
    76
    +0.13
    0.7%
    346
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.21
    0.02
    452
    +0.13
    0.04
    442
    +0.13
    0.05
    Negative Logits
    quart
    -1.63
    ESULT
    -1.57
    áĢº
    -1.51
    áĢ¬
    -1.48
    ude
    -1.41
     somewhere
    -1.40
    etting
    -1.40
    à«ĩ
    -1.37
    igraphy
    -1.35
    à±ģ
    -1.33
    POSITIVE LOGITS
    gage
    1.56
    ths
    1.44
    acity
    1.37
     Constitution
    1.30
    gree
    1.26
     Dock
    1.25
     capacity
    1.24
    ox
    1.23
    ¾
    1.23
     departed
    1.21
    Activations Density 0.557%

    No Known Activations