© 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. 25876
    Prev
    Next
    INDEX
    Explanations

    the word "it" in various contexts throughout the text

    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
    +0.18
    1.0%
    165
    +0.14
    0.8%
    376
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.17
    441
    +0.14
    0.09
    156
    +0.13
    0.11
    Negative Logits
    Ŀ
    -1.93
    Ļ
    -1.89
    Ļª
    -1.76
    ¤
    -1.68
    wick
    -1.67
    ®
    -1.63
    ļ
    -1.63
    °
    -1.60
    »¿
    -1.58
    ľ
    -1.56
    POSITIVE LOGITS
     accidentally
    1.95
    alian
    1.95
     restart
    1.87
    chy
    1.80
     erroneously
    1.73
     mistakenly
    1.63
     suddenly
    1.61
     randomly
    1.61
     permanently
    1.55
     negatively
    1.55
    Activations Density 0.747%

    No Known Activations