© 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. 8-RES-JB
    11. 4240
    Prev
    Next
    INDEX
    Explanations

    mentions of political positions or titles in the context of a government role

    oai_token-act-pair · gpt-3.5-turbo

    references to the presidency and the role of the president

    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
    abel
    -0.75
    _>
    -0.73
     scrim
    -0.70
    emis
    -0.66
     spotting
    -0.65
     locating
    -0.65
     lia
    -0.64
    wards
    -0.63
     trickle
    -0.62
     specialize
    -0.62
    POSITIVE LOGITS
     United
    1.24
    United
    1.17
     nation
    1.16
     country
    1.10
     Commonwealth
    1.04
     Republic
    1.03
     UNITED
    1.02
     republic
    0.99
     Philippines
    0.99
     Confederacy
    0.94
    Activations Density 0.297%

    No Known Activations