© 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. 26549
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "sudden."

    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
    387
    +0.14
    0.8%
    350
    +0.12
    0.7%
    156
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.14
    0.01
    452
    +0.12
    0.02
    56
    +0.12
    0.00
    Negative Logits
    ublic
    -1.50
    emon
    -1.47
    ubl
    -1.46
    obo
    -1.45
    ILITY
    -1.45
    efore
    -1.42
     predominantly
    -1.41
    UC
    -1.41
    eneath
    -1.40
    ecause
    -1.39
    POSITIVE LOGITS
    Ł
    2.59
    ij
    2.29
    ĨĴ
    2.26
    ¡
    2.18
    £
    2.12
    ¨
    2.07
    ¢
    2.03
    ¥
    1.95
    ±
    1.92
    ķ
    1.89
    Activations Density 0.105%

    No Known Activations