© 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. 11504
    Prev
    Next
    INDEX
    Explanations

    phrases related to shutting down or closing operations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "shut down" 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
    Lay
    -0.71
    ãĤ©
    -0.67
    arov
    -0.66
    ry
    -0.63
    orthy
    -0.63
    Catalog
    -0.63
    present
    -0.61
    antine
    -0.61
    umper
    -0.61
    OD
    -0.60
    POSITIVE LOGITS
     altogether
    0.86
     shop
    0.82
     indefinitely
    0.80
     hostilities
    0.78
    river
    0.76
     abruptly
    0.76
     operations
    0.76
     temporarily
    0.72
     entirely
    0.70
     Interstate
    0.70
    Activations Density 0.078%

    No Known Activations