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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 14831
    Prev
    Next
    INDEX
    Explanations

    video-related terms or mentions, perhaps indicating a focus on video content analysis

    oai_token-act-pair · gpt-3.5-turbo

    references to video content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sole
    -0.80
    ston
    -0.80
    isin
    -0.76
     bed
    -0.70
    neg
    -0.68
    separ
    -0.68
    utherford
    -0.67
    wit
    -0.63
     wedge
    -0.63
     contention
    -0.63
    POSITIVE LOGITS
     Videos
    1.53
     WATCHED
    0.98
     Thumbnails
    0.94
     Video
    0.86
     Watching
    0.85
     Killed
    0.84
     Downloads
    0.84
     videos
    0.81
     VIDEOS
    0.80
     -->
    0.79
    Activations Density 0.004%

    No Known Activations