© 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. 11-RES-JB
    11. 22638
    Prev
    Next
    INDEX
    Explanations

    phrases related to political negotiations and strategies

    oai_token-act-pair · gpt-3.5-turbo

    legislative processes and political maneuvering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uner
    -0.96
     Clicker
    -0.73
     voy
    -0.73
     paed
    -0.72
     colonialism
    -0.72
    nex
    -0.71
     enqu
    -0.70
    cyclop
    -0.70
    advertising
    -0.69
     civilisation
    -0.69
    POSITIVE LOGITS
     Boehner
    1.71
     McConnell
    1.65
    Republicans
    1.63
     Republicans
    1.63
    Democrats
    1.62
     Democrats
    1.62
    Senate
    1.60
     Senate
    1.54
     GOP
    1.54
     Dems
    1.50
    Activations Density 0.581%

    No Known Activations