© 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. 11-RES-JB
    11. 22328
    Prev
    Next
    INDEX
    Explanations

    hyperlinks starting with "www"

    oai_token-act-pair · gpt-3.5-turbo

    URLs related to websites

    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
    ThumbnailImage
    -1.00
    ò
    -0.99
    ortunately
    -0.99
    Þ
    -0.98
     oun
    -0.96
     eleph
    -0.96
    aditional
    -0.95
     practition
    -0.90
     exting
    -0.90
    oreAnd
    -0.90
    POSITIVE LOGITS
    natureconservancy
    1.05
    ebin
    1.03
    youtu
    0.98
    forums
    0.92
    ctl
    0.92
    www
    0.91
    usercontent
    0.88
    archive
    0.88
    sonian
    0.87
    youtube
    0.87
    Activations Density 0.022%

    No Known Activations