© 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. 0-RES-JB
    11. 11359
    Prev
    Next
    INDEX
    Explanations

    references to content going viral on the internet

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to viral content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kens
    -0.70
    oug
    -0.69
    fort
    -0.68
    hammer
    -0.68
    ridge
    -0.68
    uity
    -0.67
     Option
    -0.66
    estate
    -0.66
    oire
    -0.66
     Temper
    -0.65
    POSITIVE LOGITS
     viral
    3.71
    iral
    1.58
     virus
    1.50
     viruses
    1.46
     infectious
    1.44
     contagious
    1.38
     memes
    1.33
     vir
    1.32
     Virus
    1.29
     Vir
    1.28
    Activations Density 0.021%

    No Known Activations