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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2648
    Prev
    Next
    INDEX
    Explanations

    links to YouTube videos

    oai_token-act-pair · gpt-3.5-turbo

    YouTube video URLs

    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
    byss
    -0.63
    ĪĴ
    -0.62
     tracts
    -0.62
    ufact
    -0.62
     delegation
    -0.59
    heit
    -0.58
    ston
    -0.58
     bip
    -0.57
    insula
    -0.57
     asphalt
    -0.57
    POSITIVE LOGITS
    youtube
    0.97
    youtu
    0.89
    embed
    0.89
    videos
    0.81
     Videos
    0.81
    watch
    0.77
    iframe
    0.72
    feature
    0.72
     Youtube
    0.71
    results
    0.70
    Activations Density 0.029%

    No Known Activations