© 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. 12860
    Prev
    Next
    INDEX
    Explanations

    words related to endings, conclusions, or finality

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "closure"

    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
    nis
    -0.86
    inen
    -0.72
    yah
    -0.72
    yton
    -0.72
    olf
    -0.71
    orum
    -0.71
    icist
    -0.70
    arat
    -0.70
    kaya
    -0.70
    uld
    -0.70
    POSITIVE LOGITS
     shroud
    0.85
     closures
    0.77
    closure
    0.77
    Closure
    0.75
     lid
    0.73
     shutter
    0.73
     curtains
    0.72
    ãĤ¬
    0.72
     postponed
    0.72
     closure
    0.68
    Activations Density 0.021%

    No Known Activations