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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14403
    Prev
    Next
    INDEX
    Explanations

    words related to warnings or dangers

    oai_token-act-pair · gpt-3.5-turbo

    the concept of dangers in various contexts

    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
    onement
    -0.87
    ership
    -0.83
    BN
    -0.80
    eric
    -0.78
    ergy
    -0.75
    eb
    -0.75
    brance
    -0.72
    ced
    -0.71
    owned
    -0.70
    eds
    -0.70
    POSITIVE LOGITS
     pitfalls
    1.04
     dangers
    0.95
     undermin
    0.95
    afety
    0.93
     lurking
    0.92
     hazards
    0.84
     consequences
    0.80
     disadvant
    0.78
     harms
    0.77
     endanger
    0.77
    Activations Density 0.010%

    No Known Activations