© 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. 12-RES-JB
    11. 4429
    Prev
    Next
    INDEX
    Explanations

    vulnerabilities and security risks in software applications

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    technical terminology related to cybersecurity vulnerabilities and exploits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    aukee
    -0.82
     masc
    -0.78
    ointment
    -0.72
    asca
    -0.71
    rentices
    -0.71
    ynes
    -0.70
    estial
    -0.69
    union
    -0.68
    Í
    -0.68
    áµ
    -0.68
    POSITIVE LOGITS
     CVE
    2.05
    CVE
    2.00
     vulnerabilities
    1.85
     vulnerability
    1.82
     vulner
    1.70
     exploit
    1.52
    ulnerability
    1.50
    ulner
    1.49
     patched
    1.45
     exploits
    1.44
    Activations Density 0.319%

    No Known Activations