© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3747
    Prev
    Next
    INDEX
    Explanations

    HTML/CSS class names and related tags

    oai_token-act-pair · gpt-3.5-turbo

    elements and attributes related to HTML and web development structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McCoy
    -0.86
     KR
    -0.80
     DAC
    -0.78
     Balt
    -0.78
     Everett
    -0.77
     WCS
    -0.76
     Bradford
    -0.73
     Fas
    -0.73
     Cumber
    -0.71
     CPUs
    -0.71
    POSITIVE LOGITS
    Button
    1.37
    btn
    1.36
    button
    1.32
     toolbar
    1.23
    title
    1.21
    Label
    1.17
    heading
    1.17
    "><
    1.16
    menu
    1.15
    hover
    1.15
    Activations Density 0.116%

    No Known Activations