Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 16149
    Prev
    Next
    INDEX
    Explanations

    mentions of the platform "YouTube" and interactions related to it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of YouTube and related videos

    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
    sembly
    -0.78
    izational
    -0.72
     Pats
    -0.68
    urion
    -0.66
     Ballard
    -0.66
     quarters
    -0.65
    hart
    -0.63
    rieg
    -0.63
    rocal
    -0.63
    omaly
    -0.63
    POSITIVE LOGITS
     clips
    1.05
     videos
    1.03
     Video
    0.97
     Videos
    0.95
     clip
    0.95
    YouTube
    0.93
     Clip
    0.91
     Channel
    0.87
    plays
    0.87
    Video
    0.86
    Activations Density 0.036%

    No Known Activations