© 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. 12776
    Prev
    Next
    INDEX
    Explanations

    words related to high-resolution display technology, specifically focusing on terms like 4K and HD

    oai_token-act-pair · gpt-3.5-turbo

    specifications related to display resolutions and technology

    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
    ulla
    -0.71
    é¾įå
    -0.71
    arius
    -0.71
    reprene
    -0.69
    cules
    -0.68
    esta
    -0.68
    nuts
    -0.68
    ItemTracker
    -0.68
    bag
    -0.67
    involved
    -0.67
    POSITIVE LOGITS
     1080
    1.25
     playback
    1.18
     HDR
    1.13
    1080
    1.11
     codec
    1.08
     TVs
    1.08
     1280
    1.06
     visuals
    1.05
     resolution
    1.04
     HD
    1.03
    Activations Density 0.101%

    No Known Activations