© 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. 1-RES-JB
    11. 3675
    Prev
    Next
    INDEX
    Explanations

    instances of exploitation in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to 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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucket
    -0.85
    cone
    -0.80
    board
    -0.79
    gran
    -0.77
    upon
    -0.72
    arat
    -0.70
    arta
    -0.69
    semble
    -0.67
    andro
    -0.67
    seller
    -0.67
    POSITIVE LOGITS
     exploitation
    1.20
     exploited
    1.15
     exploiting
    1.01
     exploit
    0.88
     vulner
    0.80
    eering
    0.78
     disadvant
    0.74
    ileged
    0.73
    ãĥ¼ãĥĨãĤ£
    0.72
    iries
    0.71
    Activations Density 0.007%

    No Known Activations