© 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. 11-RES-JB
    11. 10300
    Prev
    Next
    INDEX
    Explanations

    references to the beginning or starting point of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "opening."

    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
    ieving
    -0.86
    ufact
    -0.84
    iever
    -0.79
    rome
    -0.78
    ief
    -0.78
    rior
    -0.77
    ards
    -0.77
    ronics
    -0.76
    arus
    -0.74
    ievers
    -0.73
    POSITIVE LOGITS
     ceremony
    1.07
     ceremonies
    1.07
     credits
    0.97
     weekend
    0.90
     salv
    0.89
     crawl
    0.88
     sal
    0.87
     keynote
    0.84
     rites
    0.83
     gam
    0.83
    Activations Density 0.058%

    No Known Activations