© 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. 11-RES-JB
    11. 11497
    Prev
    Next
    INDEX
    Explanations

    information related to news analysis and updates from specific regions like Israel, the Middle East, and the Jewish world

    oai_token-act-pair · gpt-3.5-turbo

    references to Israel and the Middle East news

    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
    rats
    -0.53
     inactive
    -0.52
     congr
    -0.50
    ths
    -0.49
     gravy
    -0.48
     Intermediate
    -0.48
     Weak
    -0.47
     trickle
    -0.46
    ecause
    -0.45
     immature
    -0.45
    POSITIVE LOGITS
    abad
    0.77
    tnc
    0.74
     certs
    0.66
    ãĤ¯
    0.65
    ãĤ¨ãĥ«
    0.62
    oké
    0.59
     ãĤ
    0.58
    apolis
    0.58
    ä¹
    0.57
    é»Ĵ
    0.57
    Activations Density 0.042%

    No Known Activations