© 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. 10663
    Prev
    Next
    INDEX
    Explanations

    names of viruses like Ebola and Zika

    oai_token-act-pair · gpt-3.5-turbo

    references to diseases, specifically Ebola and Zika

    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
    */(
    -0.77
    UGC
    -0.77
    ++++++++++++++++
    -0.74
    othy
    -0.72
    edom
    -0.72
    roth
    -0.70
     Zup
    -0.70
    kus
    -0.69
    hematic
    -0.67
    UTC
    -0.66
    POSITIVE LOGITS
     virus
    1.18
     outbreak
    1.06
     Virus
    1.06
     infection
    1.03
     epidemic
    1.01
     toxin
    1.00
     outbreaks
    0.99
     hemorrh
    0.97
     Outbreak
    0.95
     contag
    0.93
    Activations Density 0.037%

    No Known Activations