© 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. 10-RES-JB
    11. 3069
    Prev
    Next
    INDEX
    Explanations

    mentions of the political party "Labour."

    oai_token-act-pair · gpt-3.5-turbo

    references to the Labour Party and its leader, particularly related to political actions and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.79
    EStream
    -0.77
    ilation
    -0.73
     Bezos
    -0.73
     Toledo
    -0.72
     Indianapolis
    -0.71
    Columb
    -0.71
    Downloadha
    -0.70
    .$
    -0.69
     Filipino
    -0.69
    POSITIVE LOGITS
     Party
    1.28
     MPs
    1.24
     MP
    0.98
     parliamentary
    0.95
    shire
    0.95
     Leader
    0.95
    Leader
    0.94
     councillors
    0.94
    Labour
    0.93
    Party
    0.93
    Activations Density 0.023%

    No Known Activations