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. 19604
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    references to political cases and controversies

    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
    âĢ
    -1.01
    é¾įåĸļ士
    -0.95
    ï¸
    -0.93
    ÂŃ
    -0.89
    âĸº
    -0.86
    âĶĢ
    -0.82
    âĢij
    -0.79
     âĢ
    -0.78
     
    -0.77
    âĢIJ
    -0.77
    POSITIVE LOGITS
     JFK
    1.04
     NYT
    0.97
     Oprah
    0.96
     idiots
    0.89
     Illuminati
    0.86
     negro
    0.84
     libel
    0.83
     CIA
    0.83
     congress
    0.83
     assass
    0.83
    Activations Density 1.602%

    No Known Activations