© 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. 4-RES-SM
    11. 10960
    Prev
    Next
    INDEX
    Explanations

    instances of logging or log-related terminology

    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
    307
    +0.17
    0.9%
    18
    +0.12
    0.6%
    269
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.17
    0.01
    148
    +0.12
    0.01
    349
    +0.12
    0.02
    Negative Logits
    ly
    -1.82
    prot
    -1.67
    ftware
    -1.59
     subsidiary
    -1.43
    hift
    -1.42
    adium
    -1.40
    ÅĤa
    -1.39
    liness
    -1.38
    umab
    -1.35
     bid
    -1.35
    POSITIVE LOGITS
    ged
    2.96
    istical
    2.72
    istics
    2.71
    ging
    2.71
    gers
    2.68
    ical
    2.55
    othet
    2.40
    £
    2.32
    ģ
    2.20
    Ķ
    2.17
    Activations Density 0.194%

    No Known Activations