© 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. 28313
    Prev
    Next
    INDEX
    Explanations

    references to giveaways or contests

    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
    108
    +0.12
    0.7%
    427
    +0.11
    0.6%
    489
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    399
    +0.12
    0.01
    66
    +0.11
    0.02
    351
    +0.11
    0.02
    Negative Logits
    ylase
    -1.66
     neither
    -1.64
    under
    -1.64
     absence
    -1.55
     ease
    -1.54
    oflu
    -1.53
     nothing
    -1.53
     none
    -1.52
     heavy
    -1.51
     separate
    -1.51
    POSITIVE LOGITS
    µ
    3.04
    ·¸
    2.74
    ¼
    2.68
    ↵↵
    2.67
    <|outofrange|>
    2.67
    ↵
    2.67
    ↵↵
    2.67
     ↵
    2.67
    ↵
    2.67
    ↵
    2.67
    Activations Density 0.258%

    No Known Activations