© 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. 9009
    Prev
    Next
    INDEX
    Explanations

    mentions of the politician Bobby Jindal

    oai_token-act-pair · gpt-3.5-turbo

    the name "Jindal" related to events and contexts involving him

    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
    ogene
    -0.85
    ibel
    -0.83
    icle
    -0.81
    illon
    -0.77
    uper
    -0.73
    ope
    -0.72
    claim
    -0.71
    inct
    -0.71
    ruary
    -0.71
    icles
    -0.70
    POSITIVE LOGITS
     nomine
    1.02
     Jindal
    0.80
    tions
    0.74
    ©¶æ
    0.70
    anova
    0.70
     Louie
    0.69
    ©¶æ¥µ
    0.68
     immersion
    0.67
    £ı
    0.65
    TIT
    0.64
    Activations Density 0.022%

    No Known Activations