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

    Neuronpedia

    APICircuit 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. 10-RES-JB
    6. 4037
    Prev
    Next
    INDEX
    Explanations

    mentions of specific people's or characters' names

    oai_token-act-pair · gpt-3.5-turbo

    significant names and events related to political discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neighborhood
    -1.00
     colors
    -0.96
     honors
    -0.95
     neighboring
    -0.94
     neighborhoods
    -0.94
     railroad
    -0.94
     specialized
    -0.92
     flavors
    -0.91
     color
    -0.90
     odor
    -0.90
    POSITIVE LOGITS
     UKIP
    1.69
    Labour
    1.66
     Corbyn
    1.61
     Ukip
    1.60
     Farage
    1.52
     Labour
    1.51
    Brexit
    1.48
    Scotland
    1.47
    £
    1.47
     MPs
    1.43
    Activations Density 1.106%

    No Known Activations