© 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. 1-RES-SM
    11. 27466
    Prev
    Next
    INDEX
    Explanations

    instances of the term "vertex" and variations related to graphics or shader programming

    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
    37
    +0.16
    0.9%
    85
    +0.14
    0.8%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.16
    0.02
    410
    +0.14
    0.03
    59
    +0.12
    0.02
    Negative Logits
    Īĺ
    -1.73
    ĸ´
    -1.57
     separation
    -1.49
    hower
    -1.47
     conditioning
    -1.42
    bil
    -1.42
    80211
    -1.37
     '';
    -1.35
     '</
    -1.34
    ophosph
    -1.33
    POSITIVE LOGITS
    arian
    2.06
    apine
    1.92
    ideos
    1.87
    icip
    1.83
    ue
    1.73
    ions
    1.66
    ian
    1.64
    ienne
    1.63
    icul
    1.59
     professions
    1.58
    Activations Density 0.268%

    No Known Activations