© 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. 9-RES-JB
    11. 9125
    Prev
    Next
    INDEX
    Explanations

    text related to public health statements and government health departments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of health-related announcements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     emphas
    -0.83
     scept
    -0.81
    olkien
    -0.81
     favourites
    -0.80
     flavours
    -0.79
     flavour
    -0.78
     Corbyn
    -0.77
    colour
    -0.77
     realise
    -0.76
     realised
    -0.76
    POSITIVE LOGITS
     statewide
    1.09
     wastewater
    1.05
     inspections
    0.98
     repairs
    0.94
     cleanup
    0.91
     staffing
    0.89
     residential
    0.88
     federally
    0.87
     hazardous
    0.87
     sewer
    0.87
    Activations Density 1.646%

    No Known Activations