© 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. 28186
    Prev
    Next
    INDEX
    Explanations

    references to clinical contexts or studies

    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
    156
    +0.20
    1.1%
    87
    +0.14
    0.8%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.20
    0.02
    71
    +0.14
    0.02
    88
    +0.12
    0.01
    Negative Logits
    urope
    -1.47
    quo
    -1.46
    refs
    -1.44
    endor
    -1.44
     pristine
    -1.36
    als
    -1.36
    wers
    -1.29
    quilibrium
    -1.29
    conom
    -1.29
    acking
    -1.24
    POSITIVE LOGITS
     suite
    1.65
    ities
    1.62
    ised
    1.50
    tri
    1.49
    -âĤ¬
    1.48
    ourse
    1.47
    istically
    1.45
     setup
    1.45
    ties
    1.45
     inspector
    1.44
    Activations Density 0.043%

    No Known Activations