© 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. 11-RES-JB
    11. 1946
    Prev
    Next
    INDEX
    Explanations

    information related to government, politics, and events in Michigan

    oai_token-act-pair · gpt-3.5-turbo

    references to government entities and their actions

    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
    Cruz
    -1.11
     Fiji
    -1.04
     Icelandic
    -1.04
     Cruz
    -1.02
     Iceland
    -1.00
    Ãį
    -1.00
    Turkish
    -0.94
     avocado
    -0.91
     Rohing
    -0.91
     Ecuador
    -0.90
    POSITIVE LOGITS
     Detroit
    2.29
    Detroit
    2.22
     Michigan
    1.94
     Lansing
    1.85
    Michigan
    1.83
     Pistons
    1.80
     Wolver
    1.76
     Flint
    1.70
     Mich
    1.61
     Snyder
    1.50
    Activations Density 0.301%

    No Known Activations