© 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. 9-RES-JB
    11. 2283
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety, security, and priority

    oai_token-act-pair · gpt-3.5-turbo

    statements emphasizing priorities related to safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imore
    -0.70
    azo
    -0.69
     dup
    -0.68
    uge
    -0.66
    ograms
    -0.66
     traces
    -0.65
    ugh
    -0.64
     previews
    -0.64
     resemblance
    -0.62
     reprint
    -0.61
    POSITIVE LOGITS
     priority
    1.45
     paramount
    1.45
     priorities
    1.24
    priority
    1.18
     concern
    1.03
     cornerstone
    0.95
     Priority
    0.95
     overriding
    0.92
     imperative
    0.91
     issue
    0.89
    Activations Density 0.447%

    No Known Activations