© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5113
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Corbyn"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific political figure

    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
    .�
    -0.90
    �
    -0.90
     �
    -0.83
    aho
    -0.75
     --
    -0.68
     Title
    -0.67
     honor
    -0.67
     Vis
    -0.67
    aband
    -0.67
     travelers
    -0.65
    POSITIVE LOGITS
     Corbyn
    3.74
    byn
    2.10
     Miliband
    2.04
     Farage
    1.78
     Labour
    1.71
    Brexit
    1.68
    Labour
    1.67
     Macron
    1.62
     Brexit
    1.58
     Ukip
    1.55
    Activations Density 0.013%

    No Known Activations