© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-SM
    11. 12276
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "How do."

    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
    48
    +0.16
    0.9%
    295
    +0.16
    0.9%
    263
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.16
    0.04
    48
    +0.16
    0.03
    267
    +0.12
    0.02
    Negative Logits
    Ļª
    -3.28
    ¼
    -2.98
    ĨĴ
    -2.84
    §
    -2.50
    »
    -2.44
    »¿
    -2.43
    ¾
    -2.39
    £
    -2.28
    ¶
    -2.25
    ·¸
    -2.19
    POSITIVE LOGITS
     your
    1.91
    ppler
    1.84
    xygen
    1.79
     yours
    1.78
    ugin
    1.66
    zing
    1.64
     things
    1.62
     you
    1.61
     |
    1.57
     anything
    1.55
    Activations Density 0.029%

    No Known Activations