© 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. 4-RES-JB
    11. 24215
    Prev
    Next
    INDEX
    Explanations

    phrases related to closure or shutting down

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "close" in various contexts

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

    No Comments

    Negative Logits
    inen
    -0.69
    anse
    -0.66
    ager
    -0.66
    ãĥīãĥ©ãĤ´ãĥ³
    -0.65
    ial
    -0.64
    icist
    -0.63
    ä¸
    -0.63
    intend
    -0.63
    reme
    -0.62
    Catalog
    -0.62
    POSITIVE LOGITS
     loopholes
    0.86
     doors
    0.83
     Doors
    0.77
     curtains
    0.76
     shutter
    0.74
     auctions
    0.70
     Closing
    0.70
    doors
    0.67
    âĸ¬
    0.67
     closing
    0.65
    Activations Density 0.020%

    No Known Activations