© 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. 12605
    Prev
    Next
    INDEX
    Explanations

    phrases related to construction, production, investigation, response, and development

    oai_token-act-pair · gpt-3.5-turbo

    terms related to production and construction activities

    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
     Teach
    -0.66
    âĹ¼
    -0.66
    CRE
    -0.65
    ionage
    -0.65
    hemy
    -0.65
    aunder
    -0.65
    ãģĦ
    -0.62
    SAY
    -0.61
    SHARE
    -0.60
    ãģĨ
    -0.60
    POSITIVE LOGITS
     commenced
    1.49
     resumed
    1.38
     begins
    1.32
     lasted
    1.32
     underway
    1.29
     began
    1.24
     lasts
    1.21
     progressed
    1.21
     resumes
    1.20
     proceeded
    1.19
    Activations Density 0.425%

    No Known Activations