© 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. 7-RES-JB
    11. 19231
    Prev
    Next
    INDEX
    Explanations

    words related to watching, viewing, or browsing content

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to viewing or watching content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suscept
    -0.78
     Berm
    -0.77
     sprung
    -0.69
    hood
    -0.67
    cill
    -0.66
    recy
    -0.66
     towed
    -0.63
     coupling
    -0.63
     mantle
    -0.62
     arming
    -0.61
    POSITIVE LOGITS
     VIDEOS
    0.92
     videos
    0.91
     movies
    0.90
     DVDs
    0.87
     Movies
    0.82
     clips
    0.79
     subtitles
    0.79
     ads
    0.79
     advertisements
    0.78
     Watching
    0.78
    Activations Density 0.197%

    No Known Activations