© 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. 9-RES-JB
    11. 18221
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal documents and formal procedures

    oai_token-act-pair · gpt-3.5-turbo

    sequences that indicate the presence of an end of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vulner
    -0.57
     practise
    -0.55
     Vaugh
    -0.52
     tatt
    -0.51
     spreads
    -0.51
     guarding
    -0.50
     advoc
    -0.50
     stretches
    -0.49
    avorite
    -0.48
     Sark
    -0.47
    POSITIVE LOGITS
     RELEASE
    0.71
     Robots
    0.66
     Forums
    0.65
    displayText
    0.65
     Quote
    0.64
     largeDownload
    0.63
    fml
    0.62
     Written
    0.61
     Beginning
    0.61
     Scene
    0.61
    Activations Density 0.132%

    No Known Activations