Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 18848
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent acts involving weapons

    oai_token-act-pair · gpt-3.5-turbo

    references to armed individuals and weapon-related terminology

    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
     pairing
    -0.77
    inctions
    -0.76
    omen
    -0.75
    iments
    -0.74
    ablishment
    -0.72
    ansion
    -0.71
    RGB
    -0.71
     Transactions
    -0.70
    Aren
    -0.70
    gradation
    -0.70
    POSITIVE LOGITS
     scissors
    1.21
     clipboard
    1.20
     torches
    1.20
     knives
    1.20
     guns
    1.09
     knife
    1.09
     suitcase
    1.06
     pistols
    1.05
     cane
    1.01
     rifle
    1.01
    Activations Density 0.354%

    No Known Activations