© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 11357
    Prev
    Next
    INDEX
    Explanations

    legal terms and organizations, such as laws, agencies, and intelligence networks

    oai_token-act-pair · gpt-3.5-turbo

    references to legal acts and official organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ______
    -0.71
    inventoryQuantity
    -0.68
    whel
    -0.66
    kees
    -0.66
    vae
    -0.65
    jriwal
    -0.64
    vas
    -0.63
    ategories
    -0.63
    folk
    -0.63
    aeper
    -0.62
    POSITIVE LOGITS
     constellation
    0.86
     ("
    0.79
     consortium
    0.77
     telecommunications
    0.71
     nightclub
    0.71
     acronym
    0.69
     program
    0.69
     multinational
    0.68
     Directorate
    0.67
     Initiative
    0.66
    Activations Density 0.556%

    No Known Activations