© 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. 9-RES-JB
    11. 18477
    Prev
    Next
    INDEX
    Explanations

    information related to credit, acknowledgments, and mention

    oai_token-act-pair · gpt-3.5-turbo

    promotional content for products or events

    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
     intermedi
    -0.77
     indiscrim
    -0.71
     discredited
    -0.71
     milit
    -0.70
     unamb
    -0.70
     nonexistent
    -0.70
    llah
    -0.69
     sharply
    -0.69
     perceived
    -0.68
     exacerb
    -0.68
    POSITIVE LOGITS
     Updates
    1.08
     Theme
    1.06
     Features
    1.05
     Releases
    1.04
     Credits
    1.02
     Announce
    1.00
     Reviews
    0.99
     Featured
    0.98
     Contents
    0.98
     Newsletter
    0.97
    Activations Density 0.739%

    No Known Activations