© 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. 2-RES-SM
    11. 13939
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "is"

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    81
    +0.18
    1.0%
    136
    +0.11
    0.6%
    430
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.18
    0.03
    81
    +0.11
    0.03
    86
    +0.11
    0.03
    Negative Logits
    ĻĤ
    -2.81
    ±
    -2.79
    ģ
    -2.58
    ł
    -2.58
    Ģ
    -2.57
    ´
    -2.52
    »
    -2.52
    ĨĴ
    -2.43
    ¦
    -2.41
    ¬
    -2.33
    POSITIVE LOGITS
    chemia
    2.29
    rael
    2.26
    omerase
    1.89
    lation
    1.85
    heries
    1.83
    hev
    1.83
    omal
    1.74
    opropyl
    1.73
    lam
    1.72
    consin
    1.72
    Activations Density 0.142%

    No Known Activations