© 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. 2-RES-JB
    11. 12531
    Prev
    Next
    INDEX
    Explanations

    phrases related to endings or closures

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "closing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĵĺ
    -0.78
    inen
    -0.75
    Catalog
    -0.73
    ãĥīãĥ©ãĤ´ãĥ³
    -0.71
    icist
    -0.70
    onne
    -0.69
    cia
    -0.69
    eva
    -0.67
    Kay
    -0.67
    Ware
    -0.64
    POSITIVE LOGITS
     closing
    1.00
     shutter
    0.93
     doors
    0.92
     closures
    0.88
     curtains
    0.86
     clos
    0.84
     Closing
    0.79
     closes
    0.79
     deadlines
    0.75
     Doors
    0.75
    Activations Density 0.012%

    No Known Activations