© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 17108
    Prev
    Next
    INDEX
    Explanations

    XML-related terms in text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of XML and its related concepts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.80
    rontal
    -0.78
    ãĥĦ
    -0.76
    ör
    -0.70
    rost
    -0.70
    uten
    -0.69
    politics
    -0.69
    xtap
    -0.68
    keeper
    -0.68
    itars
    -0.67
    POSITIVE LOGITS
    Http
    1.15
     XML
    1.01
     Protocol
    0.75
    oS
    0.74
     RFC
    0.71
     parser
    0.71
     markup
    0.71
     parsing
    0.69
     tags
    0.68
     pars
    0.68
    Activations Density 0.007%

    No Known Activations