© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1-RES-JB
    11. 20498
    Prev
    Next
    INDEX
    Explanations

    names related to Indian politics, especially focusing on the Bharatiya Janata Party (BJP) and individuals affiliated with it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Bharatiya Janata Party (BJP) and related entities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    resses
    -0.79
     CLSID
    -0.75
    changes
    -0.71
    ovie
    -0.70
    STD
    -0.70
    draft
    -0.68
    ugen
    -0.67
    haust
    -0.65
    phis
    -0.63
    dress
    -0.62
    POSITIVE LOGITS
     Bhar
    1.46
     mathemat
    0.88
    ucha
    0.87
    aband
    0.85
    ati
    0.84
     Lank
    0.81
    awan
    0.81
    thal
    0.77
    athi
    0.76
    anan
    0.76
    Activations Density 0.008%

    No Known Activations