Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 18268
    Prev
    Next
    INDEX
    Explanations

    sentence fragments that contain a specific character "Ċ" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    instances of political criticism and controversy

    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
     eleph
    -0.95
     neighb
    -0.91
     experimenting
    -0.90
     waterfall
    -0.87
     photograp
    -0.87
     describ
    -0.85
     paddle
    -0.85
     lookout
    -0.85
     metic
    -0.84
     reluct
    -0.84
    POSITIVE LOGITS
    Republicans
    2.00
    Democrats
    1.97
    Obama
    1.87
    Hillary
    1.85
    President
    1.80
    Americans
    1.80
    Polit
    1.80
    Congress
    1.79
    Republican
    1.79
    Senator
    1.79
    Activations Density 0.363%

    No Known Activations