© 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. 8-RES-JB
    11. 4213
    Prev
    Next
    INDEX
    Explanations

    descriptions related to life-threatening medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases concerning life-threatening conditions and their severity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -0.80
     Cree
    -0.67
     Cotton
    -0.67
     Leone
    -0.65
     Ces
    -0.64
     Polk
    -0.63
     Mock
    -0.61
     Salvador
    -0.61
     Fey
    -0.60
     BCC
    -0.59
    POSITIVE LOGITS
    saving
    1.28
    cycle
    1.25
    cycles
    1.15
    sized
    1.13
    span
    1.04
    changing
    1.03
    termin
    1.00
    time
    0.99
    threatening
    0.99
    loving
    0.98
    Activations Density 0.049%

    No Known Activations