© 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. 7-RES-JB
    11. 1643
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies published in the Proceedings of the National Academy of Sciences

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific studies and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    baugh
    -0.74
     brim
    -0.70
    ucc
    -0.70
    zsche
    -0.68
     recl
    -0.63
     cars
    -0.63
     bathrooms
    -0.63
     wand
    -0.63
    rower
    -0.63
     campuses
    -0.62
    POSITIVE LOGITS
    ãĥ¢
    0.88
    ŀ
    0.85
    Launch
    0.78
    âĶģ
    0.78
    æĸ¹
    0.74
    SPONSORED
    0.74
    :{
    0.73
    èª
    0.73
    æĹ
    0.72
     Conference
    0.71
    Activations Density 0.083%

    No Known Activations