© 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. 9-RES-JB
    11. 5779
    Prev
    Next
    INDEX
    Explanations

    keywords related to leaks and releases of sensitive information

    oai_token-act-pair · gpt-3.5-turbo

    references to classified or sensitive documents

    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
     masc
    -0.85
     newcomer
    -0.70
    Distance
    -0.70
     caring
    -0.65
     gradient
    -0.63
     substit
    -0.62
     mell
    -0.61
     instinct
    -0.61
    ¥µ
    -0.60
    mare
    -0.60
    POSITIVE LOGITS
     trove
    1.40
     leaked
    1.28
     incrim
    1.25
     declass
    1.20
     archives
    1.20
     WikiLeaks
    1.14
     documents
    1.11
     Documents
    1.10
     redacted
    1.09
     unearthed
    1.08
    Activations Density 0.492%

    No Known Activations