© 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. 9158
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Obama"

    oai_token-act-pair · gpt-3.5-turbo

    references to Barack Obama

    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
     Flavoring
    -0.78
    ļ
    -0.72
    âĵĺ
    -0.72
    Ö¼
    -0.70
    olulu
    -0.70
    asma
    -0.69
     Newcastle
    -0.68
    onyms
    -0.67
    veyard
    -0.66
     Edinburgh
    -0.66
    POSITIVE LOGITS
    Obama
    1.03
     Obama
    0.97
     administration
    0.91
     Administration
    0.81
     Barack
    0.81
    Care
    0.79
     Jinping
    0.78
     presidency
    0.77
     advisor
    0.76
    sonian
    0.73
    Activations Density 0.033%

    No Known Activations