© 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. 2-RES-JB
    11. 1356
    Prev
    Next
    INDEX
    Explanations

    mentions of UK politicians, political parties, and related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to UK political figures and governmental roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Indiana
    -0.71
     Hawai
    -0.69
    Texas
    -0.66
    Zip
    -0.66
    AAAA
    -0.65
    Enlarge
    -0.63
    Newsletter
    -0.62
    rollment
    -0.62
    {"
    -0.62
    Device
    -0.62
    POSITIVE LOGITS
     criticised
    1.04
     centre
    1.03
     organisers
    1.01
     programme
    1.01
     £
    1.00
     organise
    1.00
     organised
    0.99
     organising
    0.99
     apologised
    0.97
     emphas
    0.97
    Activations Density 3.878%

    No Known Activations