© 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 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. 11-RES-JB
    11. 7503
    Prev
    Next
    INDEX
    Explanations

    terms related to cybersecurity and cyber threats

    oai_token-act-pair · gpt-3.5-turbo

    references to cyber threats and cybersecurity

    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
     Clement
    -0.84
    erer
    -0.65
     Taste
    -0.65
     Zucker
    -0.64
     Couch
    -0.63
     LINE
    -0.62
     Peb
    -0.61
     Flav
    -0.61
     Erie
    -0.59
     uncond
    -0.59
    POSITIVE LOGITS
    netic
    1.66
    punk
    1.46
    crime
    1.39
    attacks
    1.35
    security
    1.34
    crim
    1.26
    threat
    1.25
    weapons
    1.23
    criminal
    1.22
    bull
    1.21
    Activations Density 0.031%

    No Known Activations