© 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. 9-RES-JB
    11. 5394
    Prev
    Next
    INDEX
    Explanations

    political and government-related terms and entities

    oai_token-act-pair · gpt-3.5-turbo

    references to political party affiliations and the actions of leadership, particularly relating to Trump and the Republican Party

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iability
    -0.78
    MpServer
    -0.73
    ãĤ¨ãĥ«
    -0.69
     Finder
    -0.67
    ournals
    -0.67
    actual
    -0.66
    é¾įåĸļ士
    -0.66
    tics
    -0.64
    ateurs
    -0.62
     Rite
    -0.62
    POSITIVE LOGITS
     administrations
    1.05
     administration
    1.04
     appoint
    0.96
     Administration
    0.94
     initiatives
    0.89
     policymakers
    0.88
     legisl
    0.88
     policies
    0.87
     presidency
    0.87
     enactment
    0.87
    Activations Density 0.476%

    No Known Activations