© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1761
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named Rubio in a political context, with a strong focus on the individual's quotes and actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the politician Marco Rubio

    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
     à¨
    -0.95
    à¨
    -0.80
    Ö¼
    -0.71
    ļ
    -0.70
    VERTISEMENT
    -0.65
     antioxid
    -0.64
     Elven
    -0.64
     Celt
    -0.63
    lehem
    -0.63
    arers
    -0.61
    POSITIVE LOGITS
     Rubio
    1.07
    xtap
    0.85
    bite
    0.80
    Cruz
    0.78
    cair
    0.74
    enstein
    0.73
    bish
    0.73
     Cruz
    0.73
     fielded
    0.70
    cius
    0.69
    Activations Density 0.005%

    No Known Activations