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. 0-RES-JB
    6. 21296
    Prev
    Next
    INDEX
    Explanations

    references to judicial entities and proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to the judiciary system and related committees

    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
     pans
    -0.69
    addon
    -0.66
     sticker
    -0.63
     tag
    -0.62
     creep
    -0.61
    ong
    -0.61
     realise
    -0.60
     cycl
    -0.60
    uer
    -0.59
     cleaner
    -0.59
    POSITIVE LOGITS
     Judiciary
    3.60
     judiciary
    2.05
     Judicial
    1.80
     Grassley
    1.53
     Oversight
    1.40
     Appropriations
    1.40
     judicial
    1.35
     Courts
    1.35
     Legislation
    1.30
    iciary
    1.28
    Activations Density 0.011%

    No Known Activations