© 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. 0-RES-JB
    11. 6627
    Prev
    Next
    INDEX
    Explanations

    HTML tags within a document

    oai_token-act-pair · gpt-3.5-turbo

    references to HTML coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conserv
    -0.79
     contested
    -0.73
     Bay
    -0.68
     stabil
    -0.67
     imped
    -0.65
     occup
    -0.64
     compet
    -0.64
     occupation
    -0.64
     conservation
    -0.64
     venture
    -0.64
    POSITIVE LOGITS
    html
    3.88
    htm
    2.73
     html
    2.04
    tml
    1.98
    php
    1.94
    aspx
    1.86
    HTML
    1.84
    pdf
    1.71
    xml
    1.58
    css
    1.50
    Activations Density 0.011%

    No Known Activations