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

    Neuronpedia

    APICircuit 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. 3-RES-JB
    6. 1660
    Prev
    Next
    INDEX
    Explanations

    phrases related to weapons

    oai_token-act-pair · gpt-3.5-turbo

    references to 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 @ 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
     Strawberry
    -0.76
    TO
    -0.71
    âĸ¬
    -0.71
    noon
    -0.71
    BACK
    -0.71
    Adams
    -0.69
    mons
    -0.69
    ŃĶ
    -0.68
     Beckham
    -0.68
    Flickr
    -0.68
    POSITIVE LOGITS
     weapons
    0.96
     arsenal
    0.91
    chwitz
    0.89
     smugglers
    0.87
     caches
    0.86
     installations
    0.83
     systems
    0.82
     levers
    0.82
     stockpile
    0.81
     shipments
    0.79
    Activations Density 0.016%

    No Known Activations