© 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. 2549
    Prev
    Next
    INDEX
    Explanations

    mentions of Hillary Clinton and her email server controversy

    oai_token-act-pair · gpt-3.5-turbo

    references to Hillary Clinton's email practices and related 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
     Spock
    -0.90
     Corsair
    -0.89
    jriwal
    -0.86
     Nietzsche
    -0.82
     Tooth
    -0.82
     Radeon
    -0.81
     Optimus
    -0.80
     Canaver
    -0.80
    zsche
    -0.78
    agos
    -0.77
    POSITIVE LOGITS
     Rodham
    1.28
    clinton
    1.27
    INTON
    1.26
    Clinton
    1.22
     Clinton
    1.21
     Huma
    1.18
     Clintons
    1.13
    Hillary
    1.11
     Hillary
    1.10
     Monica
    1.04
    Activations Density 0.248%

    No Known Activations