© 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 EvalsExportsinterp-engineNEWAPI 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. 22947
    Prev
    Next
    INDEX
    Explanations

    quotations from news programs

    oai_token-act-pair · gpt-3.5-turbo

    quotes from interviews and news segments

    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
    etsy
    -0.77
     bloom
    -0.73
    PDF
    -0.72
     literature
    -0.71
     sealing
    -0.70
     shipping
    -0.70
     handwriting
    -0.69
     binding
    -0.68
     dens
    -0.68
     pamphlet
    -0.68
    POSITIVE LOGITS
     Tonight
    1.23
    Radio
    1.13
    radio
    1.11
     MSNBC
    1.09
    Morning
    1.04
     Hannity
    1.04
     CNBC
    1.04
     broadcasts
    1.04
     Radio
    1.02
     broadcaster
    1.01
    Activations Density 0.476%

    No Known Activations