© 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. 11-RES-JB
    11. 7873
    Prev
    Next
    INDEX
    Explanations

    references to political leaders or high-ranking officials

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political leaders and their relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Denver
    -1.11
     comet
    -0.91
     Weld
    -0.88
    Pokemon
    -0.88
     Comet
    -0.85
    stanbul
    -0.84
     Boulder
    -0.84
     Pokemon
    -0.84
    Magikarp
    -0.82
     Denver
    -0.82
    POSITIVE LOGITS
     Rwanda
    1.98
     Uganda
    1.93
     Congo
    1.91
     Rw
    1.81
     Zimbabwe
    1.81
     Tanzania
    1.69
     Ug
    1.65
     Africans
    1.64
     Zamb
    1.63
     Kenya
    1.63
    Activations Density 0.488%

    No Known Activations