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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 3518
    Prev
    Next
    INDEX
    Explanations

    words related to disease outbreaks

    oai_token-act-pair · gpt-3.5-turbo

    references to disease outbreaks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ajo
    -0.81
    ibur
    -0.73
     pronouns
    -0.68
    orem
    -0.67
    ilts
    -0.65
    shaw
    -0.64
    nda
    -0.64
    estamp
    -0.64
    inx
    -0.63
     pedest
    -0.63
    POSITIVE LOGITS
     outbreak
    1.14
     Outbreak
    1.05
     outbreaks
    0.90
    eers
    0.82
     virus
    0.76
     prevention
    0.76
     epidemic
    0.72
     infect
    0.71
     Epidem
    0.71
     epidem
    0.70
    Activations Density 0.020%

    No Known Activations