© 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. 4-RES-SM
    11. 11760
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the absence of significant differences or effects in clinical studies

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    243
    +0.13
    0.7%
    498
    +0.12
    0.7%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    54
    +0.13
    0.06
    356
    +0.12
    0.06
    52
    +0.11
    0.04
    Negative Logits
    mith
    -1.50
     eBay
    -1.50
     sake
    -1.49
     offline
    -1.49
     abroad
    -1.46
     mechanics
    -1.44
     blockchain
    -1.44
     Paper
    -1.43
    érie
    -1.37
     GOOGLE
    -1.36
    POSITIVE LOGITS
    »¿
    4.58
    ĨĴ
    4.56
    ĻĤ
    4.46
    Ľ
    4.34
    Ĭ
    4.30
    4.29
    4.29
    4.29
    ↵
    4.29
    č↵
    4.29
    Activations Density 0.407%

    No Known Activations