© 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. 26574
    Prev
    Next
    INDEX
    Explanations

    key numerical values and important identifiers in technical or administrative contexts

    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
    263
    +0.14
    0.8%
    247
    +0.13
    0.7%
    233
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.14
    0.10
    247
    +0.13
    0.10
    420
    +0.13
    0.06
    Negative Logits
    Ļª
    -3.33
    Īĺ
    -3.13
    ĭ
    -2.87
    ĥ
    -2.76
    ĨĴ
    -2.66
    ľĵ
    -2.62
    IJ
    -2.59
    Ŀ
    -2.55
    ĸ
    -2.54
    ģ
    -2.53
    POSITIVE LOGITS
    ↵
    1.82
    ↵
    1.70
    ↵
    1.64
    ↵
    1.64
    ↵
    1.57
    ↵		↵
    1.54
     Field
    1.48
     Photo
    1.48
     ↵
    1.43
    ↵
    1.40
    Activations Density 2.250%

    No Known Activations