© 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. 24489
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cheat" in various forms

    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
    368
    +0.11
    0.6%
    310
    +0.11
    0.6%
    75
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.11
    0.02
    109
    +0.11
    0.01
    466
    +0.11
    0.01
    Negative Logits
    00000
    -1.57
    à¯ģ
    -1.53
    heimer
    -1.52
     else
    -1.52
    ize
    -1.48
    ://
    -1.47
     reasons
    -1.45
    olving
    -1.44
    à³
    -1.43
    à¯į
    -1.43
    POSITIVE LOGITS
    eration
    1.60
     win
    1.51
     schedule
    1.44
    ery
    1.44
    encies
    1.39
    chen
    1.38
    erated
    1.35
    ering
    1.33
    ifer
    1.30
    pless
    1.30
    Activations Density 0.108%

    No Known Activations