© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18858
    Prev
    Next
    INDEX
    Explanations

    phrases related to risks to lives or health

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to risk and life-threatening situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Smooth
    -0.67
    */(
    -0.66
    ugal
    -0.65
    olid
    -0.64
     stride
    -0.63
    ALSE
    -0.63
    enium
    -0.62
     Deadline
    -0.62
     motions
    -0.62
    soType
    -0.61
    POSITIVE LOGITS
     endangered
    1.12
     forfeit
    1.11
     jeopard
    1.07
     jeopardy
    1.06
    angering
    1.05
     endanger
    1.03
     sacrificed
    1.02
     harmed
    1.00
     hostage
    1.00
     peril
    0.99
    Activations Density 0.262%

    No Known Activations