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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 5630
    Prev
    Next
    INDEX
    Explanations

    mentions of weapons

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annel
    -0.72
    Row
    -0.70
    borough
    -0.68
    jee
    -0.68
     Oprah
    -0.65
    gae
    -0.64
     âĶľ
    -0.64
    displayText
    -0.63
    rss
    -0.63
    gow
    -0.62
    POSITIVE LOGITS
     weapons
    3.56
    weapons
    2.94
     Weapons
    2.83
     weaponry
    2.76
    Weapons
    2.62
     weapon
    2.57
    weapon
    2.23
     firearms
    2.13
     guns
    2.13
     Weapon
    1.99
    Activations Density 0.021%

    No Known Activations