© 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. 4-RES-SM
    11. 14145
    Prev
    Next
    INDEX
    Explanations

    mentions of the letter 'G' in various contexts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    412
    +0.14
    0.8%
    271
    +0.12
    0.7%
    306
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.14
    0.06
    460
    +0.12
    0.04
    10
    +0.12
    0.05
    Negative Logits
    ction
    -1.79
     itself
    -1.55
    omycin
    -1.50
    coming
    -1.49
    paration
    -1.48
    naments
    -1.47
    aintiff
    -1.41
    amente
    -1.41
     millenn
    -1.39
    sender
    -1.37
    POSITIVE LOGITS
    ithub
    2.20
    rowing
    2.07
    astric
    2.06
    ossip
    2.04
    uitar
    1.96
    ambling
    1.90
    REEK
    1.84
    arrison
    1.77
    athering
    1.73
    uten
    1.73
    Activations Density 0.065%

    No Known Activations