© 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. 7751
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific political figure named "Rand Paul"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the individual Rand Paul

    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
     dism
    -0.70
    uated
    -0.64
    urally
    -0.62
     clay
    -0.62
    ysis
    -0.60
    ded
    -0.59
     sleepy
    -0.59
     marrow
    -0.58
     circadian
    -0.58
     drag
    -0.58
    POSITIVE LOGITS
    olph
    1.39
    uin
    1.18
    wick
    1.10
    stad
    1.04
    olf
    1.04
    igan
    0.93
    alls
    0.87
    rand
    0.86
    emonium
    0.85
    yth
    0.84
    Activations Density 0.031%

    No Known Activations