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. 10-RES-JB
    6. 23737
    Prev
    Next
    INDEX
    Explanations

    mentions of the legal status of various activities in different states

    oai_token-act-pair · gpt-3.5-turbo

    references to legal statuses and regulations across different regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.90
    0000000000000000
    -0.86
    inventoryQuantity
    -0.78
    VP
    -0.76
    oola
    -0.75
    wagon
    -0.74
    FontSize
    -0.74
    çͰ
    -0.71
     è£ıè
    -0.71
    ãĤ©
    -0.71
    POSITIVE LOGITS
     Germany
    1.30
     Switzerland
    1.30
     countries
    1.27
     Denmark
    1.26
     France
    1.24
     Finland
    1.21
     England
    1.20
     jurisdictions
    1.20
     Britain
    1.19
     Ireland
    1.19
    Activations Density 0.279%

    No Known Activations