© 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. 20894
    Prev
    Next
    INDEX
    Explanations

    words related to international conflicts and sanctions

    oai_token-act-pair · gpt-3.5-turbo

    topics related to economic crises and financial accountability

    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
    :(
    -0.64
     000
    -0.63
     upl
    -0.63
     educate
    -0.62
    :[
    -0.62
     Seah
    -0.61
     FAC
    -0.61
     PW
    -0.60
     ILCS
    -0.60
     Bis
    -0.60
    POSITIVE LOGITS
    Brexit
    1.06
     Russia
    0.89
     Bashar
    0.87
     resurg
    0.87
    Russia
    0.87
     Vladimir
    0.86
     Brexit
    0.85
     Kremlin
    0.84
    Islam
    0.84
    Putin
    0.84
    Activations Density 0.294%

    No Known Activations