© 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. 0-RES-JB
    11. 9465
    Prev
    Next
    INDEX
    Explanations

    HTML anchor tags ("<a href=") with URLs

    oai_token-act-pair · gpt-3.5-turbo

    HTML anchor tags or hyperlinks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ster
    -0.72
     reckoning
    -0.69
    bos
    -0.60
    wine
    -0.60
     Tray
    -0.59
    unda
    -0.58
     Booth
    -0.57
     orderly
    -0.57
     punishment
    -0.57
     Cub
    -0.56
    POSITIVE LOGITS
     href
    4.25
    href
    2.09
    inventoryQuantity
    1.08
    url
    1.06
    actionDate
    1.05
     Retrieved
    1.03
    tnc
    1.01
    20439
    1.01
     url
    0.99
     ItemLevel
    0.97
    Activations Density 0.010%

    No Known Activations