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. 2-RES-JB
    6. 227
    Prev
    Next
    INDEX
    Explanations

    the term "exploit" within various contexts

    oai_token-act-pair · gpt-4-turbo

    phrases related to technology exploits

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "exploit" in various contexts related to vulnerabilities and opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arat
    -0.85
    present
    -0.72
    cas
    -0.66
    ael
    -0.65
    reads
    -0.65
    birth
    -0.65
    ometown
    -0.65
    ophy
    -0.65
    prints
    -0.64
     captcha
    -0.63
    POSITIVE LOGITS
    oit
    1.11
     exploit
    1.01
    ulner
    0.87
     loopholes
    0.86
     exploits
    0.86
    ãĥ¼ãĥĨãĤ£
    0.85
     exploiting
    0.83
    CVE
    0.83
     weaknesses
    0.83
     exploited
    0.82
    Activations Density 0.011%

    No Known Activations