© 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. 4-RES-JB
    11. 17102
    Prev
    Next
    INDEX
    Explanations

    phrases related to government and political processes

    oai_token-act-pair · gpt-3.5-turbo

    references to "government" and discussions around its role, actions, and policies

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

    No Comments

    Negative Logits
    ammers
    -0.79
     Brah
    -0.77
     Ryu
    -0.75
    ifer
    -0.74
    ãģķ
    -0.74
    lihood
    -0.70
     Samson
    -0.68
     Nielsen
    -0.68
    Magikarp
    -0.67
     Haram
    -0.67
    POSITIVE LOGITS
     shutdown
    1.03
    ahime
    0.90
    ework
    0.79
     Accountability
    0.77
    uliffe
    0.75
     appropriations
    0.75
    ilogy
    0.75
     conservatism
    0.74
     elected
    0.74
     oversight
    0.73
    Activations Density 0.074%

    No Known Activations