© 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. 28310
    Prev
    Next
    INDEX
    Explanations

    references to software or modular components

    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
    392
    +0.15
    0.8%
    389
    +0.13
    0.7%
    327
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.15
    0.02
    389
    +0.13
    0.02
    327
    +0.12
    0.02
    Negative Logits
     same
    -1.74
    cology
    -1.59
    WHERE
    -1.59
     Commonwealth
    -1.57
     behalf
    -1.57
    oming
    -1.51
     Leone
    -1.45
     utmost
    -1.43
     invading
    -1.43
     United
    -1.37
    POSITIVE LOGITS
    Ĩ
    2.35
    º
    2.28
    Į
    2.15
    ifier
    2.12
    ¿½
    2.01
    ifies
    1.99
    ¾
    1.96
    Ĵ
    1.95
    erne
    1.94
    «
    1.91
    Activations Density 0.038%

    No Known Activations