© 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. 26853
    Prev
    Next
    INDEX
    Explanations

    references to prominent individuals and entities in political or social 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/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
    235
    +0.16
    0.9%
    419
    +0.14
    0.8%
    395
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.16
    0.14
    33
    +0.14
    0.12
    395
    +0.14
    0.12
    Negative Logits
    ª
    -1.70
    gal
    -1.39
    Ļ
    -1.39
    /-
    -1.38
    ¼
    -1.35
    ¿
    -1.35
     capacities
    -1.33
    gaard
    -1.32
     tastes
    -1.28
    ·¸
    -1.26
    POSITIVE LOGITS
     him
    1.56
     ours
    1.48
    ordered
    1.48
     yours
    1.42
     ahead
    1.41
    uler
    1.40
    licts
    1.38
     negotiations
    1.33
    équ
    1.31
    ellar
    1.28
    Activations Density 3.807%

    No Known Activations