© 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. 26239
    Prev
    Next
    INDEX
    Explanations

    references to various courses and educational programs

    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
    499
    +0.12
    0.6%
    209
    +0.11
    0.6%
    361
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    20
    +0.12
    0.03
    499
    +0.11
    0.03
    468
    +0.11
    0.03
    Negative Logits
    ĥ½
    -3.85
    ·
    -3.77
    ĻĤ
    -3.68
    ±
    -3.67
    ¥
    -3.48
    ¯
    -3.48
    ·¸
    -3.42
    §
    -3.37
    Ĵ
    -3.37
    µ
    -3.32
    POSITIVE LOGITS
    work
    1.70
    ymal
    1.69
    ters
    1.67
    meal
    1.59
    maker
    1.57
    utorial
    1.56
    iness
    1.50
    yl
    1.49
    finder
    1.49
    uation
    1.48
    Activations Density 0.172%

    No Known Activations