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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10849
    Prev
    Next
    INDEX
    Explanations

    phrases related to large groups of people congregating or involved in events, protests, or demonstrations

    oai_token-act-pair · gpt-3.5-turbo

    references to large groups of people participating in events or protests

    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
    Recomm
    -0.80
    Adds
    -0.71
    gets
    -0.66
    Words
    -0.65
    Planet
    -0.65
    Rating
    -0.64
    $.
    -0.63
     Realms
    -0.62
    powers
    -0.62
    ologies
    -0.62
    POSITIVE LOGITS
     rallied
    1.31
     marched
    1.31
     protested
    1.23
     gathered
    1.22
     gather
    1.11
     chanted
    1.10
     stormed
    1.09
     descended
    1.05
     attended
    1.05
     waved
    1.04
    Activations Density 0.083%

    No Known Activations