© 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. 8-RES-JB
    11. 5103
    Prev
    Next
    INDEX
    Explanations

    YouTube video URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs specifically related to YouTube video links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.89
     Wonderland
    -0.69
     Sins
    -0.64
     Dull
    -0.63
    HAM
    -0.61
     aisle
    -0.61
    ï¸ı
    -0.61
     Goods
    -0.60
    hill
    -0.59
     McCl
    -0.59
    POSITIVE LOGITS
    watch
    1.01
    youtube
    0.89
    channel
    0.76
    youtu
    0.73
     Youtube
    0.73
    user
    0.71
     livestream
    0.71
    htt
    0.70
     playback
    0.70
    save
    0.68
    Activations Density 0.028%

    No Known Activations