© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 3441
    Prev
    Next
    INDEX
    Explanations

    instances of firing, shooting, and related actions involving weapons

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of firing weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hai
    -0.79
    lihood
    -0.71
    Merit
    -0.69
    folk
    -0.68
    DragonMagazine
    -0.66
    advertising
    -0.65
    imgur
    -0.64
    女
    -0.64
    arth
    -0.64
    Label
    -0.64
    POSITIVE LOGITS
     gunshots
    1.27
     shots
    1.22
     bullets
    1.21
     projectiles
    1.16
     missiles
    1.13
     volley
    1.05
     arrows
    1.04
     pellets
    1.03
    bomb
    1.01
     gunfire
    1.01
    Activations Density 0.068%

    No Known Activations