© 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. 7349
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures, specifically focusing on members of the Gandhi political dynasty

    oai_token-act-pair · gpt-3.5-turbo

    references to specific political figures, particularly members of the Gandhi family in India

    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
     Scotia
    -0.90
     Concord
    -0.88
    foundland
    -0.80
    tower
    -0.69
    apult
    -0.67
    olphins
    -0.67
    VALUE
    -0.66
    apeake
    -0.66
    enegger
    -0.65
    FTWARE
    -0.65
    POSITIVE LOGITS
     Gandhi
    1.03
    uled
    0.88
     Rahul
    0.88
    uling
    0.83
     Sharma
    0.82
    monary
    0.82
    igans
    0.81
    udeau
    0.79
    icide
    0.77
    pora
    0.75
    Activations Density 0.011%

    No Known Activations