© 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. 12-RES-JB
    11. 3810
    Prev
    Next
    INDEX
    Explanations

    information related to violent incidents involving weapons

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to gunfire or shooting incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    女
    -0.70
    imgur
    -0.68
     Beir
    -0.67
    advertising
    -0.66
    Merit
    -0.65
    hai
    -0.64
     Taxi
    -0.63
    hall
    -0.63
    lihood
    -0.60
    é¾įå¥ij士
    -0.60
    POSITIVE LOGITS
     shots
    1.10
     gunshots
    1.02
     pellets
    0.99
     rounds
    0.93
    bomb
    0.92
     shells
    0.89
     tear
    0.88
    shots
    0.87
     indiscrim
    0.86
     warning
    0.86
    Activations Density 0.095%

    No Known Activations