© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 7065
    Prev
    Next
    INDEX
    Explanations

    phrases related to ease, convenience, and simplicity

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to ease of use and convenience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FLAG
    -0.76
     glim
    -0.73
    shall
    -0.67
    mir
    -0.65
    oir
    -0.62
    ãĥĹ
    -0.62
    law
    -0.62
     hotly
    -0.61
     merit
    -0.61
     ferv
    -0.61
    POSITIVE LOGITS
     browsing
    1.06
     navigating
    0.97
     checkout
    0.97
     workflow
    0.96
     navigation
    0.95
     transitioning
    0.95
     customization
    0.92
     transition
    0.91
     accessing
    0.90
     uploading
    0.89
    Activations Density 0.116%

    No Known Activations