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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 12959
    Prev
    Next
    INDEX
    Explanations

    HTML tags related to dividing content into sections

    oai_token-act-pair · gpt-3.5-turbo

    references to HTML or web development elements, specifically "div" tags

    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
    hots
    -0.85
    rost
    -0.73
    KC
    -0.71
    onde
    -0.68
    OIL
    -0.67
    Hay
    -0.67
    ares
    -0.65
     Kre
    -0.65
    holm
    -0.65
     Roche
    -0.65
    POSITIVE LOGITS
     div
    3.91
    div
    2.01
     Div
    1.99
    Div
    1.85
     divid
    1.82
     Divinity
    1.22
    DIV
    1.13
     divine
    1.09
     divided
    1.04
     pag
    1.01
    Activations Density 0.018%

    No Known Activations