© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 13726
    Prev
    Next
    INDEX
    Explanations

    references to protests and protesters

    oai_token-act-pair · gpt-3.5-turbo

    references to protesters and demonstration events

    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
    æ©Ł
    -0.80
    ournal
    -0.80
    BuyableInstoreAndOnline
    -0.73
     Excellence
    -0.73
    Sense
    -0.68
    Myth
    -0.68
    ministic
    -0.68
    ãĥ¯
    -0.68
    sense
    -0.68
    âĺħâĺħ
    -0.67
    POSITIVE LOGITS
     chanting
    1.25
     chanted
    1.15
     marched
    1.12
     protesting
    1.09
     protestors
    1.08
     demonstrators
    1.02
     protesters
    1.02
     gathered
    1.01
     occupying
    1.01
     waving
    1.00
    Activations Density 0.052%

    No Known Activations