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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-RES-JB
    6. 10346
    Prev
    Next
    INDEX
    Explanations

    terms related to the Zika virus, its transmission, and associated medical information

    oai_token-act-pair · gpt-3.5-turbo

    topics related to health risks and disease transmission

    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
    Untitled
    -0.84
    Artist
    -0.82
    Marx
    -0.78
    WIND
    -0.78
    Merit
    -0.77
    Lenin
    -0.72
    Property
    -0.70
    rawdownloadcloneembedreportprint
    -0.70
    Atl
    -0.70
    Theme
    -0.69
    POSITIVE LOGITS
     medication
    1.32
     medications
    1.24
     inflammation
    1.22
     lact
    1.17
     clinically
    1.17
     carcin
    1.16
     medicines
    1.15
     allergy
    1.15
     nutritional
    1.15
     biomark
    1.14
    Activations Density 1.035%

    No Known Activations