© 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. 1283
    Prev
    Next
    INDEX
    Explanations

    legislative and political language

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative processes and community 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
    aunder
    -0.82
    estate
    -0.78
     dies
    -0.75
    ":"/
    -0.74
    ONDON
    -0.73
     ruining
    -0.73
     cling
    -0.72
     reck
    -0.71
     revenge
    -0.71
     Invalid
    -0.70
    POSITIVE LOGITS
     attendees
    1.08
     brainstorm
    1.04
    Particip
    1.03
     participants
    0.99
     collaborative
    0.92
     presentations
    0.92
     particip
    0.92
     facilit
    0.91
     workshops
    0.90
     Volunteers
    0.90
    Activations Density 1.205%

    No Known Activations