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

    Neuronpedia

    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. 11-RES-JB
    11. 9508
    Prev
    Next
    INDEX
    Explanations

    specific event names

    oai_token-act-pair · gpt-3.5-turbo

    events or competitions in sports and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iously
    -0.81
     artificially
    -0.78
    âĹ¼
    -0.76
    orically
    -0.75
    rather
    -0.73
    enough
    -0.68
    idine
    -0.68
    icidal
    -0.68
     compan
    -0.67
    onic
    -0.66
    POSITIVE LOGITS
     Recap
    1.57
     Highlights
    1.52
     Dates
    1.48
     Preview
    1.47
     Results
    1.36
     Details
    1.35
     Coverage
    1.33
     Announce
    1.33
     Begins
    1.29
     Winners
    1.27
    Activations Density 0.254%

    No Known Activations