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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 8465
    Prev
    Next
    INDEX
    Explanations

    words related to the medical condition of malaria

    oai_token-act-pair · gpt-3.5-turbo

    terms related to malaria and parasitic diseases

    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
    ARB
    -0.74
    soDeliveryDate
    -0.74
    shaw
    -0.74
    enegger
    -0.73
    essler
    -0.72
    orical
    -0.72
    CHR
    -0.71
    ATIONAL
    -0.70
    ational
    -0.70
    FTWARE
    -0.69
    POSITIVE LOGITS
     parasite
    1.31
     parasites
    1.23
    iasis
    1.04
     mosquitoes
    1.02
     mosquit
    0.98
     malaria
    0.97
    worms
    0.93
    infect
    0.91
     Paras
    0.90
     endemic
    0.87
    Activations Density 0.008%

    No Known Activations