© 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 EvalsExportsinterp-engineNEWAPI 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. 28845
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the"

    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
    98
    +0.26
    1.6%
    478
    +0.22
    1.3%
    23
    +0.18
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.26
    0.09
    98
    +0.22
    0.02
    291
    +0.18
    0.06
    Negative Logits
     quo
    -1.61
     wherein
    -1.52
    ilee
    -1.50
    posts
    -1.49
    Sov
    -1.46
    "}](#
    -1.45
    [,
    -1.37
    κε
    -1.35
    compress
    -1.34
    table
    -1.34
    POSITIVE LOGITS
    »¿
    2.50
    ĸ´
    2.29
    ľ
    2.29
    ĨĴ
    2.26
    ·¸
    2.09
    ¿½
    2.01
    ¼
    1.97
    §
    1.95
     sake
    1.94
    Ľ
    1.94
    Activations Density 0.662%

    No Known Activations