© 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. 11629
    Prev
    Next
    INDEX
    Explanations

    phrases related to critical situations or imminent dangers

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "brink" in various contexts suggesting imminent danger or critical situations

    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
     mailed
    -0.64
    ADS
    -0.64
    aughtered
    -0.60
     IMAGES
    -0.59
    reditary
    -0.59
    odor
    -0.59
    CD
    -0.59
    MN
    -0.58
     Uz
    -0.58
     archived
    -0.58
    POSITIVE LOGITS
     brink
    1.41
    manship
    1.36
     verge
    1.16
    terness
    1.06
     bluff
    0.88
    wcs
    0.82
     perspect
    0.80
    cape
    0.77
     edge
    0.74
    ï¸
    0.73
    Activations Density 0.004%

    No Known Activations