© 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. 28832
    Prev
    Next
    INDEX
    Explanations

    instances of the word "git" and variations in the context of version control

    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
    230
    +0.14
    0.8%
    397
    +0.13
    0.7%
    177
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.14
    0.02
    230
    +0.13
    0.02
    397
    +0.12
    0.01
    Negative Logits
    ancers
    -1.79
    oving
    -1.63
    looking
    -1.61
    xy
    -1.58
    rely
    -1.55
    eren
    -1.51
     ?>
    -1.46
    ances
    -1.45
     suppose
    -1.45
    ibraries
    -1.45
    POSITIVE LOGITS
    ¾
    1.84
     fide
    1.60
    Ģ
    1.60
    evo
    1.58
    freak
    1.57
    ĩ
    1.57
    book
    1.51
    chip
    1.45
    ģ
    1.45
    oire
    1.44
    Activations Density 0.127%

    No Known Activations