© 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. 3-RES-JB
    11. 564
    Prev
    Next
    INDEX
    Explanations

    mentions of firearms

    oai_token-act-pair · gpt-3.5-turbo

    references to firearms and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eff
    -0.78
    gres
    -0.76
    ishi
    -0.73
     Archdemon
    -0.71
    atom
    -0.69
    graded
    -0.67
    grad
    -0.65
    orse
    -0.64
    Mission
    -0.64
     Paramount
    -0.64
    POSITIVE LOGITS
     firearms
    1.21
     firearm
    1.08
     ammunition
    0.94
    powder
    0.90
     guns
    0.84
     handguns
    0.84
     accessories
    0.82
     Firearms
    0.81
     homicide
    0.80
     homicides
    0.80
    Activations Density 0.014%

    No Known Activations