© 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. 4-RES-SM
    11. 12924
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to analysis or 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
    78
    +0.21
    1.2%
    348
    +0.20
    1.1%
    9
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.21
    0.06
    359
    +0.20
    0.07
    502
    +0.13
    0.06
    Negative Logits
    optional
    -1.80
    unnumbered
    -1.79
    )?
    -1.76
    msgstr
    -1.74
    soever
    -1.71
    neq
    -1.65
    ?)
    -1.63
    didn
    -1.60
     weren
    -1.60
    ?”
    -1.58
    POSITIVE LOGITS
    ij
    4.50
           ↵
    4.46
    <|outofrange|>
    4.46
         ↵
    4.46
    4.46
     ↵
    4.46
    4.46
    ↵
    4.46
    ↵
    4.46
    ↵↵
    4.46
    Activations Density 0.565%

    No Known Activations