© 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. 25142
    Prev
    Next
    INDEX
    Explanations

    instances of political language related to re-election

    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
    257
    +0.13
    0.7%
    50
    +0.11
    0.6%
    331
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    366
    +0.13
    0.03
    257
    +0.11
    0.03
    331
    +0.11
    0.03
    Negative Logits
    rone
    -1.56
    fte
    -1.47
    onia
    -1.46
     sheets
    -1.46
     Forward
    -1.43
     Words
    -1.43
     outwe
    -1.40
    fff
    -1.39
    oni
    -1.38
    ogi
    -1.38
    POSITIVE LOGITS
    IJ
    3.88
    Ĥ
    3.79
    č↵
    3.62
    <|outofrange|>
    3.62
    3.62
    3.62
    ↵↵
    3.62
    ↵
    3.62
    č↵
    3.62
    ↵
    3.62
    Activations Density 0.114%

    No Known Activations