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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17781
    Prev
    Next
    INDEX
    Explanations

    events or gatherings involving a large number of people

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities of people involved in gatherings or events

    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
    terms
    -0.85
     immortality
    -0.85
    ufact
    -0.82
    inventoryQuantity
    -0.74
    Rating
    -0.70
     Dating
    -0.68
    ocol
    -0.68
    Parent
    -0.67
    Consumer
    -0.66
    ode
    -0.65
    POSITIVE LOGITS
     protesters
    1.24
     spectators
    1.20
     demonstrators
    1.19
     onlook
    1.09
     protestors
    1.09
     volunteers
    1.05
     supporters
    0.99
     attendees
    0.94
     devote
    0.94
     assembled
    0.91
    Activations Density 0.212%

    No Known Activations