© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 751
    Prev
    Next
    INDEX
    Explanations

    keywords related to infectious diseases, specifically Ebola and Zika

    oai_token-act-pair · gpt-3.5-turbo

    mentions of infectious diseases, specifically Ebola and Zika viruses

    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
     Zup
    -0.77
    UGC
    -0.73
    ¥µ
    -0.73
    roth
    -0.72
    */(
    -0.70
    ++++++++++++++++
    -0.70
    Ocean
    -0.70
    cipled
    -0.69
    ixel
    -0.69
    Reviewer
    -0.68
    POSITIVE LOGITS
     virus
    1.40
     outbreak
    1.20
     Virus
    1.20
     infection
    1.17
     toxin
    1.17
     outbreaks
    1.14
     epidemic
    1.13
     Outbreak
    1.12
     hemorrh
    1.06
     infections
    1.03
    Activations Density 0.040%

    No Known Activations