© 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. 6-RES-JB
    11. 1597
    Prev
    Next
    INDEX
    Explanations

    words related to closure or completion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "close" and its variations, indicating actions related to closure or termination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.75
    nis
    -0.71
    lain
    -0.71
    orum
    -0.68
    alis
    -0.67
    ican
    -0.67
    icist
    -0.67
    rouse
    -0.64
    ial
    -0.64
    inen
    -0.64
    POSITIVE LOGITS
     loopholes
    0.98
     doors
    0.96
     Doors
    0.91
     curtains
    0.83
     shutter
    0.81
    doors
    0.71
     abruptly
    0.70
     shop
    0.70
     down
    0.69
     door
    0.68
    Activations Density 0.031%

    No Known Activations