© 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. 0-RES-JB
    11. 4158
    Prev
    Next
    INDEX
    Explanations

    references to the term "Brexit."

    oai_token-act-pair · gpt-3.5-turbo

    references to Brexit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pant
    -0.73
     honor
    -0.71
    ushi
    -0.69
     honored
    -0.68
    --
    -0.66
     utilized
    -0.64
     sv
    -0.64
     directs
    -0.64
    nas
    -0.63
    GH
    -0.63
    POSITIVE LOGITS
     Brexit
    3.83
    Brexit
    3.25
     Corbyn
    1.67
     Ukip
    1.65
     UKIP
    1.64
     Theresa
    1.55
     Farage
    1.48
    Britain
    1.47
     Britain
    1.40
     Britons
    1.39
    Activations Density 0.015%

    No Known Activations