© 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. 27828
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "I'm" and its variations

    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
    +0.21
    1.2%
    478
    +0.19
    1.1%
    505
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.21
    0.06
    348
    +0.19
    0.06
    196
    +0.14
    0.04
    Negative Logits
    ĸ
    -2.67
    º
    -2.41
    ļ
    -2.40
    Ĵ
    -2.32
    ¢
    -2.29
    ł
    -2.25
    ¸
    -2.11
    ·¸
    -2.09
    £
    -2.06
    »¿
    -2.05
    POSITIVE LOGITS
     ok
    1.93
     hoping
    1.78
     afraid
    1.74
     gonna
    1.73
     okay
    1.70
     kidding
    1.69
     not
    1.67
     sorry
    1.64
     OK
    1.56
     awake
    1.56
    Activations Density 0.165%

    No Known Activations