© 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. 2-RES-JB
    11. 17343
    Prev
    Next
    INDEX
    Explanations

    keywords related to weaponry or military armament

    oai_token-act-pair · gpt-3.5-turbo

    references to weapons, particularly in the context of arms and military discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noon
    -0.78
     Woodward
    -0.76
    athan
    -0.75
    vent
    -0.71
     Qué
    -0.69
     Strawberry
    -0.69
     Beckham
    -0.68
    âĸ¬
    -0.68
    chron
    -0.68
     Cow
    -0.68
    POSITIVE LOGITS
     weapons
    1.00
     arsenal
    0.92
     smugglers
    0.88
     belts
    0.86
    powder
    0.85
    chwitz
    0.85
     caches
    0.82
    mith
    0.82
     systems
    0.81
     weapon
    0.80
    Activations Density 0.017%

    No Known Activations