© 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. 9928
    Prev
    Next
    INDEX
    Explanations

    references to firearms and gun-related terminology

    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
    372
    +0.11
    0.6%
    391
    +0.10
    0.6%
    377
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.11
    0.09
    372
    +0.10
    0.10
    19
    +0.10
    0.06
    Negative Logits
     DSS
    -2.04
    ·¸
    -1.86
     Kubernetes
    -1.68
    ļ
    -1.66
     DNS
    -1.66
     mucus
    -1.60
     Io
    -1.60
    ľĵ
    -1.59
    Ĩ
    -1.57
    ĨĴ
    -1.57
    POSITIVE LOGITS
     firearms
    4.29
     firearm
    4.29
     gun
    4.16
     rifle
    4.02
     rifles
    4.01
     handgun
    3.97
     pistol
    3.89
     guns
    3.87
    guns
    3.82
     shooter
    3.76
    Activations Density 1.720%

    No Known Activations