© 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. 12952
    Prev
    Next
    INDEX
    Explanations

    references to international diplomatic relations and their implications

    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
    186
    +0.21
    1.2%
    291
    +0.14
    0.8%
    210
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.21
    0.08
    178
    +0.14
    0.13
    418
    +0.13
    -0.05
    Negative Logits
    ľĵ
    -3.35
    ij
    -3.21
    Ļª
    -3.14
    ĻĤ
    -3.07
    ²
    -3.06
    ¬
    -3.04
    ¨
    -2.99
    ¥
    -2.98
    ¦
    -2.98
    ↵↵
    -2.98
    POSITIVE LOGITS
     diplomatic
    2.36
     parliament
    2.35
     parliamentary
    2.27
     Parliament
    2.09
     Putin
    2.08
     NATO
    1.99
     campaigning
    1.97
     diplomacy
    1.96
     Pakistan
    1.95
     Modi
    1.93
    Activations Density 4.390%

    No Known Activations