© 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. 9803
    Prev
    Next
    INDEX
    Explanations

    mentions of defense, military, or governmental activities

    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
    21
    +0.31
    2.0%
    156
    +0.26
    1.7%
    78
    +0.17
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.31
    0.07
    203
    +0.26
    0.07
    78
    +0.17
    -0.04
    Negative Logits
    angered
    -1.54
     Archive
    -1.52
     Legislature
    -1.51
    ortality
    -1.49
    fish
    -1.37
     autopsy
    -1.36
    onson
    -1.35
    iret
    -1.33
    ilated
    -1.32
     filmmakers
    -1.31
    POSITIVE LOGITS
     friction
    1.54
     tariffs
    1.51
     cohes
    1.50
     Mart
    1.43
     Relationship
    1.43
     Ajax
    1.40
     Stress
    1.34
     CDK
    1.33
     stress
    1.32
     UPS
    1.30
    Activations Density 3.077%

    No Known Activations