© 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. 0-RES-JB
    11. 14948
    Prev
    Next
    INDEX
    Explanations

    words related to safety and security

    oai_token-act-pair · gpt-3.5-turbo

    references to safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pond
    -0.68
     ago
    -0.65
     owe
    -0.65
     quot
    -0.63
     incarn
    -0.63
     married
    -0.63
     bundles
    -0.62
     devoted
    -0.62
     phil
    -0.62
     trump
    -0.62
    POSITIVE LOGITS
     Safety
    3.92
    Safety
    3.05
    safety
    2.79
     safety
    2.66
     SAF
    1.81
     Safe
    1.73
    afety
    1.72
    Safe
    1.57
     Stability
    1.40
     Protection
    1.39
    Activations Density 0.015%

    No Known Activations