© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 7432
    Prev
    Next
    INDEX
    Explanations

    information related to videos

    oai_token-act-pair · gpt-3.5-turbo

    elements related to video content and its characteristics

    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
    é¾įå
    -0.77
    MpServer
    -0.77
     Carbuncle
    -0.72
     Tau
    -0.71
    GW
    -0.70
    bane
    -0.70
    Collins
    -0.69
    Atl
    -0.68
     Fitzpatrick
    -0.68
     Roche
    -0.68
    POSITIVE LOGITS
     videos
    2.24
     YouTube
    2.14
    YouTube
    2.02
     video
    2.00
     Videos
    1.94
     Youtube
    1.93
     youtube
    1.91
    video
    1.84
    videos
    1.82
     Video
    1.81
    Activations Density 0.564%

    No Known Activations