© 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. 9-RES-JB
    11. 7552
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person (Marco Rubio)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Marco Rubio"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ritic
    -0.87
    sworth
    -0.81
    wich
    -0.75
    shire
    -0.73
    folk
    -0.73
    nikov
    -0.72
    suit
    -0.72
    ritis
    -0.69
    sterdam
    -0.67
    yer
    -0.67
    POSITIVE LOGITS
     Polo
    1.45
     Rubio
    1.34
     Antonio
    0.93
     Gutierrez
    0.88
     Marco
    0.85
    xtap
    0.82
     Muss
    0.79
    Fal
    0.79
    imo
    0.78
    Cruz
    0.74
    Activations Density 0.035%

    No Known Activations