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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13932
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Sean" at a significant degree of activation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Sean"

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     subp
    -0.84
    yrinth
    -0.79
     tender
    -0.78
    hov
    -0.77
     circ
    -0.72
    drm
    -0.72
    pired
    -0.70
     redeem
    -0.66
    1001
    -0.65
     situated
    -0.64
    POSITIVE LOGITS
    Sean
    1.22
     Hannity
    1.12
     Spicer
    0.97
     Sean
    0.91
     Payton
    0.87
    apon
    0.87
     Patrick
    0.85
    ason
    0.83
     Hayes
    0.83
    eman
    0.79
    Activations Density 0.008%

    No Known Activations