© 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. 2-RES-SM
    11. 13688
    Prev
    Next
    INDEX
    Explanations

    themes related to political and legislative matters

    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
    235
    +0.12
    0.7%
    346
    +0.12
    0.7%
    413
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.12
    0.07
    63
    +0.12
    0.03
    507
    +0.12
    0.01
    Negative Logits
     weren
    -1.67
     aren
    -1.65
     shelves
    -1.65
    hood
    -1.64
    webs
    -1.59
     handy
    -1.57
    pace
    -1.55
     Spectrum
    -1.52
    .","
    -1.52
     isn
    -1.52
    POSITIVE LOGITS
    »
    2.25
    ĵ
    2.19
     Parlament
    2.06
    »¿
    2.02
    ĥ
    2.02
    Ĩ
    2.00
    ©
    1.94
    Į
    1.92
    ĺ
    1.92
    ĸ
    1.91
    Activations Density 1.063%

    No Known Activations