© 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 EvalsExportsinterp-engineNEWAPI 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. 13048
    Prev
    Next
    INDEX
    Explanations

    attention-grabbing phrases indicating urgency or importance from online articles or videos

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to video content and calls to action for more videos

    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
     lett
    -0.61
     lingu
    -0.55
     recl
    -0.54
     informants
    -0.54
     typ
    -0.53
     interchange
    -0.53
     appar
    -0.52
     bean
    -0.51
     microbi
    -0.51
    bably
    -0.51
    POSITIVE LOGITS
     Videos
    1.30
     Replay
    0.87
     Thumbnails
    0.84
     Video
    0.76
    Video
    0.72
    elight
    0.71
     VIDEOS
    0.68
    videos
    0.67
    Prev
    0.66
     Photos
    0.66
    Activations Density 0.027%

    No Known Activations