© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6-RES-JB
    11. 15468
    Prev
    Next
    INDEX
    Explanations

    words related to taking advantage of situations or individuals

    oai_token-act-pair · gpt-3.5-turbo

    the concept of exploitation in various contexts

    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
    arat
    -0.80
     mint
    -0.73
    thood
    -0.71
    ucket
    -0.71
    prints
    -0.69
    cas
    -0.67
    think
    -0.65
    shake
    -0.63
    quartered
    -0.62
    semble
    -0.62
    POSITIVE LOGITS
     loopholes
    0.94
     weaknesses
    0.93
    oit
    0.91
     exploited
    0.90
    ulner
    0.83
    CVE
    0.83
     exploit
    0.83
     vulnerabilities
    0.81
     exploiting
    0.80
    oise
    0.80
    Activations Density 0.020%

    No Known Activations