© 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. 1-RES-SM
    11. 28466
    Prev
    Next
    INDEX
    Explanations

    references to components or parts of various subjects or 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/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
    502
    +0.14
    0.8%
    376
    +0.13
    0.7%
    372
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.14
    0.03
    372
    +0.13
    0.02
    62
    +0.12
    0.02
    Negative Logits
    §
    -3.52
    Ļª
    -3.30
    ľĵ
    -3.25
    ĨĴ
    -3.23
    Ń
    -3.22
    ¢
    -3.18
    ¦
    -3.16
    ´
    -3.15
    ¥
    -3.15
    ĻĤ
    -3.08
    POSITIVE LOGITS
    isans
    2.01
    ystem
    1.77
    ystems
    1.73
    icles
    1.69
    oft
    1.67
     of
    1.65
    meal
    1.61
     thereof
    1.61
     besides
    1.60
    icle
    1.57
    Activations Density 0.062%

    No Known Activations