© 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. 25405
    Prev
    Next
    INDEX
    Explanations

    references to power dynamics and governance in societal contexts

    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
    286
    +0.16
    0.9%
    442
    +0.12
    0.7%
    196
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    286
    +0.16
    0.12
    265
    +0.12
    0.07
    196
    +0.11
    0.04
    Negative Logits
    itively
    -1.64
    opically
    -1.43
    lbrack
    -1.41
    Ļª
    -1.38
    jest
    -1.36
    lect
    -1.36
    ald
    -1.36
    uet
    -1.35
    idge
    -1.31
    ille
    -1.28
    POSITIVE LOGITS
     thereof
    1.98
     alike
    1.93
     reason
    1.71
     thing
    1.63
    thing
    1.57
     portion
    1.56
    )"
    1.47
     коÑĤоÑĢ
    1.45
     source
    1.42
    '"
    1.42
    Activations Density 2.268%

    No Known Activations