© 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. 23636
    Prev
    Next
    INDEX
    Explanations

    terms related to cybersecurity and identifying security vulnerabilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cybersecurity and security-related concerns

    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
    oric
    -0.92
    hyde
    -0.84
    ICA
    -0.78
    coni
    -0.76
    oline
    -0.76
    kson
    -0.72
    lee
    -0.71
    eree
    -0.71
     Carney
    -0.70
     Kinn
    -0.68
    POSITIVE LOGITS
     vulnerabilities
    1.04
     flaws
    0.96
     breaches
    0.94
     sandbox
    0.89
     software
    0.89
     CVE
    0.87
     enhancements
    0.86
    policy
    0.86
     protocols
    0.84
     breach
    0.83
    Activations Density 0.060%

    No Known Activations