Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22986
    Prev
    Next
    INDEX
    Explanations

    phrases related to the University of Wisconsin, specifically focusing on the mentioning of "Wisconsin" and potentially locations within the university

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the University of Wisconsin and its associated entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Malays
    -1.46
     Malaysian
    -1.35
     Malaysia
    -1.32
     Kuala
    -1.27
     Cambod
    -1.21
     Singapore
    -1.17
     Manila
    -1.12
     Cambodia
    -1.12
    Egypt
    -1.07
     Myanmar
    -1.05
    POSITIVE LOGITS
     Wisconsin
    2.23
    Wisconsin
    2.19
     Milwaukee
    2.06
     Walker
    1.93
    waukee
    1.81
    Walker
    1.80
     WI
    1.76
     Madison
    1.70
    Madison
    1.68
     Wis
    1.64
    Activations Density 0.209%

    No Known Activations