© 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 EvalsExportsAPI 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. 0-RES-JB
    11. 1913
    Prev
    Next
    INDEX
    Explanations

    specific keywords related to international conventions or events

    oai_token-act-pair · gpt-3.5-turbo

    references to conventions or conferences

    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
     karma
    -0.73
     shovel
    -0.71
    ľ
    -0.70
    feed
    -0.65
     erase
    -0.64
     smoot
    -0.63
     sidel
    -0.62
     streaks
    -0.61
     earns
    -0.60
     inst
    -0.59
    POSITIVE LOGITS
     Convention
    4.01
     convention
    2.62
     conventions
    2.03
     Conference
    1.39
     Treaty
    1.37
     Expo
    1.31
     Declaration
    1.23
     treaty
    1.21
     Debate
    1.19
     Committee
    1.12
    Activations Density 0.008%

    No Known Activations