© 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 EvalsExportsAPI 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. 26588
    Prev
    Next
    INDEX
    Explanations

    references to sorting procedures and functions

    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
    249
    +0.14
    0.8%
    59
    +0.12
    0.7%
    466
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.14
    0.02
    59
    +0.12
    0.02
    18
    +0.11
    0.02
    Negative Logits
    documentclass
    -1.88
    Äij
    -1.81
    asts
    -1.81
    .")
    -1.62
     glory
    -1.60
    wards
    -1.53
    rely
    -1.52
     suffering
    -1.50
     clarity
    -1.47
    roduction
    -1.42
    POSITIVE LOGITS
    Ń
    2.43
    Ĵ
    2.42
    ³
    2.24
    ª
    2.12
    İ
    2.11
    ¥
    2.02
    »
    2.00
    £
    1.99
    ¿
    1.98
    ¤
    1.97
    Activations Density 0.108%

    No Known Activations