© 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. 1-RES-JB
    11. 22478
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically focusing on instances of the name "Hugo"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Hugo."

    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
    ickr
    -0.79
    ramid
    -0.76
    spir
    -0.69
    patrick
    -0.68
    icago
    -0.67
    akening
    -0.64
    birth
    -0.62
    Indian
    -0.62
    worn
    -0.62
    abol
    -0.61
    POSITIVE LOGITS
     Hugo
    1.53
     Chavez
    1.11
    Hug
    0.92
     Nebula
    0.81
     Paulo
    0.80
     Hou
    0.77
    enson
    0.73
     Hug
    0.70
     nominations
    0.69
     Nicolas
    0.69
    Activations Density 0.004%

    No Known Activations