Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 17532
    Prev
    Next
    INDEX
    Explanations

    keywords related to viruses and their impact

    oai_token-act-pair · gpt-3.5-turbo

    mentions of viruses, specifically focusing on their effects and implications

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

    No Comments

    Negative Logits
    rian
    -0.77
    secut
    -0.77
    ŃĶ
    -0.70
    ĻĤ
    -0.70
    minist
    -0.70
    agall
    -0.70
    agher
    -0.69
    cknow
    -0.69
    notations
    -0.67
    anooga
    -0.67
    POSITIVE LOGITS
    irus
    1.05
     virus
    1.01
     Virus
    0.98
     infection
    0.95
     outbreak
    0.93
     infections
    0.90
     Disease
    0.88
     viruses
    0.88
     disease
    0.86
     Infect
    0.84
    Activations Density 0.012%

    No Known Activations