© 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. 8-RES-JB
    11. 17177
    Prev
    Next
    INDEX
    Explanations

    mentions of 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bindings
    -0.80
    ajo
    -0.76
    lasses
    -0.76
    verbs
    -0.75
    estamp
    -0.75
    racuse
    -0.73
     Bind
    -0.71
    pees
    -0.70
    antine
    -0.66
    */(
    -0.66
    POSITIVE LOGITS
     outbreak
    1.07
     Outbreak
    1.04
    eers
    0.97
     outbreaks
    0.87
     virus
    0.87
     epidemic
    0.85
    olon
    0.83
     infect
    0.82
    eer
    0.81
     plag
    0.80
    Activations Density 0.050%

    No Known Activations