© 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. 0-RES-JB
    11. 8248
    Prev
    Next
    INDEX
    Explanations

    references to the name "Cruz" at varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Cruz."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ritic
    -0.77
    Gam
    -0.70
    windows
    -0.69
    inth
    -0.66
     Rune
    -0.65
    visual
    -0.64
    engine
    -0.63
     Autumn
    -0.63
     Gamma
    -0.63
     bulletin
    -0.63
    POSITIVE LOGITS
     Cruz
    3.82
    Cruz
    3.39
     Rubio
    1.99
     Kasich
    1.70
     Castro
    1.60
     Fiorina
    1.52
     Sanders
    1.50
     Ted
    1.48
    Ted
    1.46
     Jindal
    1.42
    Activations Density 0.022%

    No Known Activations