© 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. 4790
    Prev
    Next
    INDEX
    Explanations

    information related to specific events, possibly in the context of news or coverage

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to mourning and funerals

    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
    Jewish
    -1.09
    Jews
    -1.08
    Jew
    -1.05
    Han
    -0.99
     Shapiro
    -0.96
    York
    -0.96
     Zion
    -0.96
     Rabbi
    -0.93
     rabbi
    -0.93
     Jewish
    -0.93
    POSITIVE LOGITS
     Brazilian
    2.29
    Brazil
    2.28
     Brazil
    2.27
     Sao
    2.01
     Rousse
    1.99
    ão
    1.91
     Bras
    1.87
     Portuguese
    1.79
     Paulo
    1.78
     Rio
    1.77
    Activations Density 0.296%

    No Known Activations