© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 16350
    Prev
    Next
    INDEX
    Explanations

    words related to diseases transmitted by mosquitoes

    oai_token-act-pair · gpt-3.5-turbo

    references to diseases or conditions associated with being transmitted by mosquitoes or airborne vectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebus
    -0.77
    aminer
    -0.73
     Barnett
    -0.66
    pty
    -0.64
    Reviewer
    -0.63
     bargain
    -0.63
    Balt
    -0.61
    atalie
    -0.60
     box
    -0.59
    ofi
    -0.59
    POSITIVE LOGITS
    borne
    1.20
    cade
    0.80
     tradem
    0.75
    aukee
    0.75
    phrine
    0.73
     airborne
    0.71
    advertising
    0.71
    flies
    0.70
    mares
    0.70
    HAM
    0.70
    Activations Density 0.011%

    No Known Activations