© 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. 2-RES-JB
    11. 23716
    Prev
    Next
    INDEX
    Explanations

    references to political dictators

    oai_token-act-pair · gpt-3.5-turbo

    references to dictators and dictatorial regimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    older
    -0.83
    awks
    -0.83
    alle
    -0.80
    ilk
    -0.80
    ttp
    -0.80
    LAN
    -0.78
    atha
    -0.76
    Recommend
    -0.76
    IGH
    -0.75
    rb
    -0.75
    POSITIVE LOGITS
     dictator
    1.34
     dictatorship
    1.16
     dictators
    1.00
     nomine
    0.89
     regime
    0.85
     overth
    0.85
     regimes
    0.84
     tyrant
    0.82
     tyranny
    0.82
     overthrow
    0.81
    Activations Density 0.009%

    No Known Activations