© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28068
    Prev
    Next
    INDEX
    Explanations

    mentions of political actions or decisions regarding legislation

    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
    156
    +0.23
    1.4%
    186
    +0.21
    1.2%
    237
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.23
    0.12
    237
    +0.21
    0.17
    150
    +0.14
    0.14
    Negative Logits
     characteristic
    -1.52
    sense
    -1.51
     surroundings
    -1.50
    arily
    -1.48
     hereinafter
    -1.46
     cultures
    -1.45
    ij
    -1.42
    heses
    -1.39
    crystalline
    -1.39
    duced
    -1.38
    POSITIVE LOGITS
     funding
    1.66
     policy
    1.64
     Funding
    1.63
     sanctions
    1.58
     veto
    1.57
     “
    1.55
     controversial
    1.54
     publicly
    1.53
     ``
    1.51
     taxpayer
    1.49
    Activations Density 5.280%

    No Known Activations