© 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. 27812
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate mathematical definitions and conditions

    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
    23
    +0.27
    1.6%
    156
    +0.14
    0.8%
    96
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.27
    0.01
    96
    +0.14
    0.03
    442
    +0.12
    0.04
    Negative Logits
    ĨĴ
    -2.73
    Ķ
    -2.61
    ¸
    -2.53
    ļ
    -2.52
    »¿
    -2.39
    ĩ
    -2.38
    »
    -2.31
    Ļª
    -2.29
    Ĵ
    -2.26
    ↵
    -2.23
    POSITIVE LOGITS
    ually
    1.67
     finding
    1.63
     given
    1.60
     existence
    1.58
     positive
    1.52
    ay
    1.52
    displaystyle
    1.51
     inverse
    1.49
    ipal
    1.48
    underset
    1.47
    Activations Density 0.313%

    No Known Activations