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. 7-RES-JB
    6. 15404
    Prev
    Next
    INDEX
    Explanations

    titles or roles related to law enforcement officials

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles related to law enforcement and public safety officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    crew
    -0.70
    kiss
    -0.70
     rigging
    -0.66
     helicop
    -0.64
    ankind
    -0.63
    paid
    -0.62
     boulder
    -0.61
    perate
    -0.61
     offshore
    -0.61
    enezuel
    -0.61
    POSITIVE LOGITS
     Shaun
    1.08
     Marty
    0.99
     Sue
    0.96
     Darren
    0.95
     Darrell
    0.93
     Geoff
    0.93
     Rusty
    0.93
     Adrian
    0.92
     Kathleen
    0.92
     Stacy
    0.92
    Activations Density 0.174%

    No Known Activations