© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 18158
    Prev
    Next
    INDEX
    Explanations

    hyperlinks, specifically ones that are shared or copied in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Link."

    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
    doms
    -0.86
     Patri
    -0.79
     palate
    -0.75
    ateur
    -0.73
     interior
    -0.70
    udence
    -0.69
    ateurs
    -0.67
    exper
    -0.66
     patio
    -0.65
    leans
    -0.65
    POSITIVE LOGITS
     Link
    3.88
    Link
    2.66
     LINK
    2.00
     link
    1.96
     Links
    1.91
    link
    1.84
     linking
    1.57
     links
    1.53
    links
    1.45
     Zelda
    1.39
    Activations Density 0.011%

    No Known Activations