© 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. 13460
    Prev
    Next
    INDEX
    Explanations

    terms related to military actions and threats

    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
    +0.17
    1.0%
    186
    +0.14
    0.8%
    166
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.17
    0.04
    56
    +0.14
    -0.01
    304
    +0.14
    0.04
    Negative Logits
    ĥ½
    -3.22
    ĻĤ
    -2.90
    ¿½
    -2.80
    ľĵ
    -2.74
    ħ
    -2.72
    IJ
    -2.70
    ľ
    -2.67
    ¢
    -2.66
    ķ
    -2.65
    ©
    -2.62
    POSITIVE LOGITS
     against
    2.09
     weapon
    1.70
     opponents
    1.67
     attacks
    1.67
     threat
    1.67
     tactic
    1.66
    iveness
    1.66
     prevention
    1.63
     threats
    1.61
     demons
    1.61
    Activations Density 0.435%

    No Known Activations