© 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. 4-RES-JB
    11. 22205
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Barack 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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.75
     Cth
    -0.72
    âĵĺ
    -0.71
    vity
    -0.68
    asma
    -0.68
    ameless
    -0.67
     Edinburgh
    -0.66
     Calgary
    -0.66
    ruciating
    -0.66
     Yen
    -0.65
    POSITIVE LOGITS
    Obama
    0.82
     administration
    0.81
     Obama
    0.80
     Barack
    0.78
     appoint
    0.76
    omics
    0.74
     playbook
    0.73
    heimer
    0.72
     appointed
    0.71
    Care
    0.70
    Activations Density 0.026%

    No Known Activations