© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 10804
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions like dismantling, rolling back, and gutting policies or laws

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governmental actions and policy changes, particularly those that involve dismantling or gutting existing laws and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.77
     Arn
    -0.76
     Correspond
    -0.75
     Aires
    -0.75
     Sie
    -0.74
    Tang
    -0.71
     Beet
    -0.71
     Bie
    -0.70
    Rum
    -0.69
     Mushroom
    -0.68
    POSITIVE LOGITS
     defund
    1.03
     protections
    1.01
     Medicaid
    0.99
     funding
    0.97
     abol
    0.96
     repeal
    0.92
     unconstitutional
    0.92
     regulations
    0.91
     reforms
    0.90
    amacare
    0.90
    Activations Density 0.504%

    No Known Activations