© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 7967
    Prev
    Next
    INDEX
    Explanations

    instances of words related to closing or shutting down

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shut."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nutrition
    -0.74
    rities
    -0.72
    Reference
    -0.72
    20439
    -0.72
    lements
    -0.71
    asin
    -0.69
    alla
    -0.69
    apple
    -0.66
    ayers
    -0.66
    cific
    -0.65
    POSITIVE LOGITS
     shut
    3.82
    shut
    2.79
     Shut
    2.46
     shutting
    2.39
     shuts
    2.26
    Shut
    2.16
     shutdown
    2.04
     closed
    1.57
     shutter
    1.46
     Shutdown
    1.35
    Activations Density 0.019%

    No Known Activations