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. 14533
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS code related tokens

    oai_token-act-pair · gpt-3.5-turbo

    CSS style declarations and dimensions

    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
    £ı
    -0.80
    issance
    -0.62
     Fault
    -0.61
     Rasmussen
    -0.59
    hunter
    -0.59
     Genie
    -0.59
     NAD
    -0.58
    urst
    -0.58
    manship
    -0.57
     costing
    -0.57
    POSITIVE LOGITS
    px
    1.21
     pixels
    0.92
    pixel
    0.89
    "></
    0.84
    padding
    0.83
     horizont
    0.82
    radius
    0.81
    width
    0.81
     width
    0.80
    height
    0.80
    Activations Density 0.067%

    No Known Activations