© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 20430
    Prev
    Next
    INDEX
    Explanations

    hands holding weapons or items typically associated with criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to firearms and weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roads
    -0.67
    otten
    -0.66
     Events
    -0.66
     Revenue
    -0.64
     Ships
    -0.64
     Restaur
    -0.62
     Flavoring
    -0.62
     Regions
    -0.61
    DEM
    -0.60
     Colleges
    -0.60
    POSITIVE LOGITS
     strapped
    1.09
     clenched
    1.03
     confiscated
    0.97
     holster
    0.94
     tucked
    0.93
     leash
    0.93
     shoved
    0.91
     clipped
    0.89
    handled
    0.88
     clasp
    0.88
    Activations Density 0.206%

    No Known Activations