© 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. 7-RES-JB
    11. 22828
    Prev
    Next
    INDEX
    Explanations

    references to leaked documents and whistleblowers

    oai_token-act-pair · gpt-3.5-turbo

    references to whistleblowers and their disclosures related to surveillance or classified information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Veterinary
    -0.79
     Athletic
    -0.78
    entary
    -0.77
     offic
    -0.75
    aukee
    -0.74
     Mayo
    -0.74
     Farmers
    -0.74
    iculture
    -0.72
     Towns
    -0.72
     Patel
    -0.72
    POSITIVE LOGITS
     WikiLeaks
    1.29
     Wikileaks
    1.26
     Snowden
    1.23
    ileaks
    1.22
    Leaks
    1.22
     whistlebl
    1.14
     trove
    1.13
     revelations
    1.11
     Assange
    1.05
     leaked
    1.04
    Activations Density 0.475%

    No Known Activations