© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 4917
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Rex" at different levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Rex."

    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
    nai
    -0.68
     centimeters
    -0.66
    itter
    -0.61
    ele
    -0.59
     broadband
    -0.59
    bottom
    -0.58
    endant
    -0.58
    teenth
    -0.58
    meter
    -0.57
     slack
    -0.57
    POSITIVE LOGITS
     Rex
    4.23
    Rex
    2.85
     Tillerson
    1.20
    rex
    1.09
     Nikki
    1.08
     Exxon
    1.07
     Tycoon
    1.04
     Getty
    1.01
     Tyrann
    1.00
    xon
    0.97
    Activations Density 0.022%

    No Known Activations