© 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. 28406
    Prev
    Next
    INDEX
    Explanations

    references to feet, footwear, and related anatomical parts

    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
    309
    +0.11
    0.6%
    444
    +0.10
    0.6%
    410
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    309
    +0.11
    0.03
    164
    +0.10
    0.02
    444
    +0.10
    0.02
    Negative Logits
    ĨĴ
    -2.21
    ľĵ
    -2.03
    ķ
    -2.02
    Ŀ
    -2.00
    Ļª
    -1.99
    ĵ
    -1.99
    woke
    -1.94
    Īĺ
    -1.92
    Ń
    -1.89
    Ĺ
    -1.87
    POSITIVE LOGITS
    prints
    2.48
    notes
    2.44
    ings
    2.00
    wear
    1.97
    sie
    1.92
    stones
    1.87
    ingly
    1.84
    less
    1.82
    steps
    1.81
    boats
    1.75
    Activations Density 0.147%

    No Known Activations