© 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. 4-RES-SM
    11. 14531
    Prev
    Next
    INDEX
    Explanations

    content related to political commentary and criticism

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    +0.34
    2.1%
    48
    +0.15
    0.9%
    25
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.34
    0.12
    390
    +0.15
    0.20
    25
    +0.13
    0.20
    Negative Logits
    <|outofrange|>
    -6.93
              ↵
    -6.93
    ↵
    -6.93
    ↵
    -6.93
    <|outofrange|>
    -6.93
    -6.93
    ↵
    -6.93
    -6.93
    ↵  ³³³
    -6.93
     ↵
    -6.93
    POSITIVE LOGITS
     politic
    1.80
     NOT
    1.79
     misunderstanding
    1.75
     deserves
    1.69
     hypocr
    1.65
     deserve
    1.63
     injustice
    1.59
     NEVER
    1.56
     disrespect
    1.56
     lies
    1.55
    Activations Density 5.331%

    No Known Activations