Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 21486
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to cybersecurity and security-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cybersecurity and security-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oric
    -0.93
    kson
    -0.78
    hes
    -0.75
    ICA
    -0.75
    ting
    -0.67
    shire
    -0.65
    phrine
    -0.65
    slow
    -0.64
    uku
    -0.64
     Kinn
    -0.63
    POSITIVE LOGITS
    policy
    0.85
     guards
    0.81
     vulnerabilities
    0.78
     breaches
    0.78
     clearance
    0.77
     lapse
    0.76
     posture
    0.76
     advis
    0.75
     Breach
    0.74
    ulence
    0.73
    Activations Density 0.031%

    No Known Activations