© 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. 4-RES-JB
    11. 20178
    Prev
    Next
    INDEX
    Explanations

    keywords indicating metadata or additional information like "Description" that segregates documents by type or category

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "Description" and related content

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

    No Comments

    Negative Logits
    ulously
    -0.77
    zig
    -0.75
    aded
    -0.75
    ishment
    -0.75
    ciating
    -0.73
    gs
    -0.72
    ishing
    -0.70
    gue
    -0.70
    cific
    -0.69
    umped
    -0.68
    POSITIVE LOGITS
     Languages
    0.90
    Description
    0.87
     Details
    0.83
     Features
    0.80
     Provides
    0.79
     Changes
    0.78
    Hide
    0.77
     Definition
    0.77
     Forms
    0.77
    isine
    0.77
    Activations Density 0.042%

    No Known Activations