© 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. 10-RES-JB
    11. 7107
    Prev
    Next
    INDEX
    Explanations

    words related to emphasizing and focusing on different aspects of a topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases highlighting the importance of focus and attention in various contexts

    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
    DragonMagazine
    -0.86
    quished
    -0.84
    oland
    -0.81
    iatus
    -0.80
    osate
    -0.79
    wic
    -0.77
    emonium
    -0.76
    agues
    -0.75
    soon
    -0.75
     Lands
    -0.74
    POSITIVE LOGITS
     simplicity
    1.52
     reliability
    1.51
     usability
    1.47
     maximizing
    1.47
     efficiency
    1.45
     affordability
    1.44
     creativity
    1.43
     consistency
    1.42
     teamwork
    1.42
     responsiveness
    1.40
    Activations Density 0.428%

    No Known Activations