© 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. 27855
    Prev
    Next
    INDEX
    Explanations

    the transition words "Here" indicating key points or transitions in the text

    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
    +0.18
    1.0%
    396
    +0.14
    0.8%
    369
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    250
    +0.18
    0.03
    396
    +0.14
    0.02
    298
    +0.13
    0.03
    Negative Logits
    ilent
    -1.77
    pires
    -1.55
     pedest
    -1.44
     reserves
    -1.43
     burden
    -1.41
    ipel
    -1.39
     workforce
    -1.39
    ource
    -1.38
    PBS
    -1.36
     platform
    -1.35
    POSITIVE LOGITS
    abouts
    2.04
    after
    1.96
    tics
    1.92
    anus
    1.57
    ward
    1.56
    inafter
    1.55
     prompted
    1.49
     reass
    1.47
     asked
    1.45
    Äĩ
    1.44
    Activations Density 0.038%

    No Known Activations