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. 10-RES-JB
    6. 21963
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of visual elements or scenes, particularly focusing on specifics like textures and materials

    oai_token-act-pair · gpt-3.5-turbo

    elements related to visual details and descriptions in imagery

    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
    íķ
    -0.67
    Financial
    -0.66
    OUP
    -0.65
     quota
    -0.64
    ensable
    -0.64
    ãĤ´ãĥ³
    -0.64
    uling
    -0.64
    ãĤ¡
    -0.64
     administering
    -0.62
     scheduling
    -0.61
    POSITIVE LOGITS
     silhouette
    1.37
     silhou
    1.32
     portraits
    1.24
     skyline
    1.17
     images
    1.13
     pictures
    1.11
     textures
    1.10
     colours
    1.09
     colors
    1.08
     paintings
    1.07
    Activations Density 0.828%

    No Known Activations