© 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. 10-RES-JB
    11. 6672
    Prev
    Next
    INDEX
    Explanations

    references related to political regimes

    oai_token-act-pair · gpt-3.5-turbo

    references to regimes or authoritarian governments

    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
    lder
    -0.82
     Lent
    -0.80
    Ocean
    -0.75
    sight
    -0.71
    Nob
    -0.71
    Universal
    -0.71
    hire
    -0.70
    ritch
    -0.68
    ertodd
    -0.67
     Voy
    -0.67
    POSITIVE LOGITS
     regime
    1.02
     overthrow
    0.95
     overth
    0.93
     regimes
    0.91
     dictatorship
    0.90
     Bashar
    0.87
     dictator
    0.85
    ollah
    0.84
     crackdown
    0.83
     milit
    0.80
    Activations Density 0.059%

    No Known Activations