© 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. 24648
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "K" in the document

    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
    369
    +0.36
    2.1%
    457
    +0.14
    0.8%
    410
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.36
    0.07
    111
    +0.14
    0.05
    388
    +0.13
    0.05
    Negative Logits
     resignation
    -1.77
    cession
    -1.75
    ception
    -1.73
    ploy
    -1.67
    abases
    -1.64
    cess
    -1.60
    cluding
    -1.57
    ployment
    -1.56
    cip
    -1.52
    bellum
    -1.51
    POSITIVE LOGITS
    Ĵ
    1.63
    ohn
    1.59
    iki
    1.54
    ĨĴ
    1.49
    inetics
    1.49
    iev
    1.45
    ernel
    1.45
    &
    1.44
    !_
    1.41
    appa
    1.41
    Activations Density 0.414%

    No Known Activations