© 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. 28798
    Prev
    Next
    INDEX
    Explanations

    information related to data structure sizes and bits

    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
    406
    +0.14
    0.8%
    249
    +0.14
    0.8%
    375
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.14
    0.02
    249
    +0.14
    0.02
    406
    +0.13
    0.02
    Negative Logits
    Ĩ
    -4.13
    ·
    -3.71
    ¸
    -3.67
    ·¸
    -3.57
    Ł
    -3.52
    ©
    -3.41
    ¼
    -3.36
    ´
    -3.32
    Ĭ
    -3.32
    ³
    -3.31
    POSITIVE LOGITS
    coins
    2.20
    worm
    2.04
    uminous
    1.97
    terness
    1.87
    bucket
    1.79
    cine
    1.73
    wise
    1.73
    meal
    1.71
    maps
    1.69
    pora
    1.67
    Activations Density 0.075%

    No Known Activations