© 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. 25641
    Prev
    Next
    INDEX
    Explanations

    attributes and properties in a structured data format

    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
    478
    +0.16
    0.9%
    380
    +0.13
    0.7%
    274
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.16
    0.04
    380
    +0.13
    0.04
    165
    +0.13
    0.03
    Negative Logits
    ](
    -1.61
    ---|---|---
    -1.57
    ocene
    -1.55
     function
    -1.53
    ---|
    -1.50
     **(
    -1.50
     */
    -1.48
     movement
    -1.43
     humans
    -1.40
    ---|---
    -1.39
    POSITIVE LOGITS
    née
    1.68
     ole
    1.62
    ľĵ
    1.62
     testosterone
    1.51
    enia
    1.48
     progesterone
    1.48
    blockList
    1.47
    lee
    1.40
    nar
    1.40
    Į
    1.39
    Activations Density 0.121%

    No Known Activations