© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27219
    Prev
    Next
    INDEX
    Explanations

    the phrase "I've got."

    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
    478
    +0.15
    0.8%
    23
    +0.14
    0.8%
    510
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.15
    0.02
    442
    +0.14
    0.03
    335
    +0.13
    0.02
    Negative Logits
    ī
    -2.46
    Ĵ
    -2.40
    ł
    -2.26
    ¤
    -2.21
    ĨĴ
    -2.19
    Ļª
    -2.17
    §
    -2.17
    ¼
    -2.14
    ¡
    -2.10
    »
    -2.06
    POSITIVE LOGITS
     veins
    1.63
     breadth
    1.56
     ideas
    1.50
     truths
    1.49
    hire
    1.49
     curiosity
    1.48
    going
    1.45
     dignity
    1.44
     been
    1.42
     faith
    1.42
    Activations Density 0.222%

    No Known Activations