© 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. 14990
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research and medical studies conducted by various research teams and institutions

    oai_token-act-pair · gpt-3.5-turbo

    prepositional phrases indicating affiliations or associations with institutions or researchers

    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
    é»Ĵ
    -0.74
     ceilings
    -0.69
    0000000000000000
    -0.69
    usercontent
    -0.69
    ascript
    -0.68
    gamer
    -0.68
    Thumbnail
    -0.66
    Shop
    -0.64
    200000
    -0.64
     kneeling
    -0.63
    POSITIVE LOGITS
     Cornell
    1.33
     Stanford
    1.32
     Rutgers
    1.31
     Princeton
    1.31
     Johns
    1.31
     Yale
    1.30
     Carnegie
    1.30
     Harvard
    1.30
     NYU
    1.28
     Vanderbilt
    1.27
    Activations Density 0.095%

    No Known Activations