© 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. 23490
    Prev
    Next
    INDEX
    Explanations

    phrases indicating online interactions, such as adding items to a cart or posting comments

    oai_token-act-pair · gpt-3.5-turbo

    signals or commands related to account management and user actions on a website

    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
     doubling
    -0.70
     hoard
    -0.69
     undermin
    -0.69
     spokes
    -0.67
     eleph
    -0.67
     civilisation
    -0.66
     ageing
    -0.65
     leaping
    -0.65
     diving
    -0.64
     torches
    -0.64
    POSITIVE LOGITS
    Learn
    0.93
    Disclaimer
    0.90
    Posted
    0.90
    ³³³
    0.89
    SELECT
    0.88
    Overview
    0.87
    posted
    0.85
    Rate
    0.85
    Please
    0.84
    Purchase
    0.84
    Activations Density 0.319%

    No Known Activations