© 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. 2937
    Prev
    Next
    INDEX
    Explanations

    words associated with causing significant events or reactions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with igniting or sparking events and changes

    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
    é¾įå
    -0.68
    éĸ
    -0.62
    oped
    -0.61
    esan
    -0.61
     rendered
    -0.61
    BILITY
    -0.58
    sama
    -0.56
     Equipment
    -0.56
    çĦ
    -0.56
     narrator
    -0.56
    POSITIVE LOGITS
     controversy
    1.14
     suspicions
    1.11
     passions
    1.10
     outrage
    1.09
     pandemonium
    1.06
     panic
    1.05
     havoc
    1.04
     curiosity
    1.04
     indignation
    1.03
     riots
    1.02
    Activations Density 0.141%

    No Known Activations