© 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. 8-RES-JB
    11. 6109
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Corbyn."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Jeremy Corbyn

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tac
    -0.73
    LOAD
    -0.66
    Memory
    -0.66
     Pelicans
    -0.65
     Minotaur
    -0.65
    teenth
    -0.64
     Pacers
    -0.62
     Vengeance
    -0.60
     Plants
    -0.60
     RX
    -0.59
    POSITIVE LOGITS
     Corbyn
    1.04
    istas
    0.97
    omics
    0.87
    ites
    0.84
    ovich
    0.84
     supporters
    0.83
    byn
    0.82
    intosh
    0.80
     supporter
    0.79
     campaigned
    0.78
    Activations Density 0.024%

    No Known Activations