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. 8-RES-JB
    6. 15340
    Prev
    Next
    INDEX
    Explanations

    phrases related to political uprisings and protests

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to protests and uprisings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bilt
    -0.86
     Lifetime
    -0.75
    paste
    -0.74
    BIT
    -0.72
     omission
    -0.70
    ECD
    -0.69
    sonian
    -0.66
    illac
    -0.65
    ewater
    -0.64
    access
    -0.64
    POSITIVE LOGITS
     uprising
    1.10
     erupted
    1.03
    rained
    0.99
     erupt
    0.95
     revolt
    0.94
     protests
    0.93
     protesting
    0.93
     unrest
    0.91
     marches
    0.91
     protestors
    0.90
    Activations Density 0.124%

    No Known Activations