© 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. 22486
    Prev
    Next
    INDEX
    Explanations

    mentions of specific politicians, especially Rand Paul, and political terms like libertarianism

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their affiliations

    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
     Overwatch
    -0.88
    yna
    -0.87
     Choi
    -0.87
     showc
    -0.83
    uez
    -0.82
     BlackBerry
    -0.81
    Crew
    -0.79
    Elsa
    -0.78
    ê
    -0.77
     Zhang
    -0.77
    POSITIVE LOGITS
     Libertarian
    2.27
     libertarian
    2.26
     libertarians
    2.22
     Rand
    1.93
    Rand
    1.82
    tarians
    1.77
     Cato
    1.68
    tarian
    1.67
     Liber
    1.64
    Liber
    1.61
    Activations Density 0.260%

    No Known Activations