© 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. 28882
    Prev
    Next
    INDEX
    Explanations

    mentions of synthetic materials or ingredients

    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
    156
    +0.30
    1.8%
    430
    +0.11
    0.7%
    74
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.30
    0.01
    430
    +0.11
    0.01
    48
    +0.11
    0.01
    Negative Logits
    Å¡ÃŃ
    -1.63
    lla
    -1.61
    edly
    -1.48
    ston
    -1.45
    wor
    -1.43
    igh
    -1.41
    hy
    -1.40
    ying
    -1.39
    aster
    -1.39
    amy
    -1.38
    POSITIVE LOGITS
    ¿½
    2.24
    £
    2.08
    ĸ
    2.05
    ĻĤ
    2.03
    ĺ
    2.00
    °
    1.93
    ¤
    1.90
    ¢
    1.90
    ↵
    1.83
    1.83
    Activations Density 0.032%

    No Known Activations