© 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. 4-RES-JB
    11. 565
    Prev
    Next
    INDEX
    Explanations

    information on news articles and must-watch videos containing important or urgent topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the urgency or importance of watching specific content, particularly videos

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

    No Comments

    Negative Logits
     intent
    -0.69
     bats
    -0.67
     lured
    -0.66
     brainstorm
    -0.65
     academia
    -0.64
    ura
    -0.64
     metro
    -0.62
     nowhere
    -0.61
     redevelopment
    -0.61
     plagiar
    -0.61
    POSITIVE LOGITS
     WATCH
    1.13
     VIDEOS
    1.02
     Thumbnails
    0.86
     WATCHED
    0.86
     Watching
    0.81
    esome
    0.80
    ARDS
    0.80
    CLASSIFIED
    0.79
    !/
    0.76
    rou
    0.75
    Activations Density 0.008%

    No Known Activations