© 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. 2-RES-JB
    11. 5902
    Prev
    Next
    INDEX
    Explanations

    terms related to the presence, spread, and effects of viruses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific virus and related medical concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥ŀ
    -0.77
    fman
    -0.76
    ezvous
    -0.74
    azeera
    -0.73
    otaur
    -0.73
    rian
    -0.73
    umn
    -0.72
    obar
    -0.72
    ĻĤ
    -0.72
    ¥µ
    -0.71
    POSITIVE LOGITS
     virus
    1.16
    irus
    1.16
     Virus
    1.02
     infection
    1.01
     infections
    0.98
     viruses
    0.97
     infect
    0.94
    worm
    0.93
     disease
    0.90
     outbreak
    0.90
    Activations Density 0.011%

    No Known Activations