© 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. 366
    Prev
    Next
    INDEX
    Explanations

    mentions of President Barack Obama's full name, with a particular emphasis on his first name "Barack"

    oai_token-act-pair · gpt-4-turbo

    the name "Barack Obama" and related terms

    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
    TOR
    -0.71
    pel
    -0.69
    Dist
    -0.69
    Bul
    -0.67
    âķIJâķIJ
    -0.66
    Ï
    -0.65
     srf
    -0.65
     subp
    -0.64
    debian
    -0.64
    Sharp
    -0.63
    POSITIVE LOGITS
     Obama
    1.14
     Hussein
    1.06
     Barack
    1.03
     Lyndon
    0.99
    Obama
    0.88
     Glenn
    0.82
     Reagan
    0.81
     Jinping
    0.81
     Trump
    0.78
     Eisenhower
    0.76
    Activations Density 0.009%

    No Known Activations