© 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
    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. 24104
    Prev
    Next
    INDEX
    Explanations

    terms related to disease transmission via mosquitoes

    oai_token-act-pair · gpt-3.5-turbo

    references to disease transmission and mosquito-borne illnesses

    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
    Artist
    -0.77
    bleacher
    -0.71
    cipled
    -0.69
     compass
    -0.69
    Clock
    -0.68
    ragon
    -0.67
    ļéĨĴ
    -0.67
    issance
    -0.67
    $$$$
    -0.66
    utra
    -0.66
    POSITIVE LOGITS
     infections
    1.39
     infection
    1.35
     disease
    1.28
     outbreaks
    1.27
     toxin
    1.27
     pathogens
    1.27
     spores
    1.26
     diseases
    1.24
     virus
    1.23
     outbreak
    1.23
    Activations Density 0.140%

    No Known Activations