© 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. 8-RES-JB
    11. 19371
    Prev
    Next
    INDEX
    Explanations

    event-related phrases such as invitations, competitions, giveaways, meetings, conferences, and celebrations

    oai_token-act-pair · gpt-3.5-turbo

    references to events and programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iple
    -0.78
    innon
    -0.72
     Nicola
    -0.72
     Toro
    -0.72
    ragon
    -0.69
     translucent
    -0.68
    eland
    -0.67
     Matte
    -0.67
    urtle
    -0.66
     Cyan
    -0.66
    POSITIVE LOGITS
     competitions
    1.14
     exhibitions
    1.11
     engagements
    1.10
     festivals
    1.06
     gatherings
    1.04
     weddings
    1.03
     contemplation
    1.02
     activities
    1.00
     concerts
    1.00
     fundra
    1.00
    Activations Density 0.464%

    No Known Activations