© 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. 7-RES-JB
    11. 1494
    Prev
    Next
    INDEX
    Explanations

    keywords related to the Microsoft Office suite

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Office" suite of products and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.81
    ulic
    -0.80
    ivals
    -0.78
    aye
    -0.77
    hma
    -0.76
    nir
    -0.76
    ipe
    -0.74
     Adin
    -0.73
    oise
    -0.72
    éĹĺ
    -0.72
    POSITIVE LOGITS
     365
    1.16
     suite
    0.93
    tops
    0.80
     suites
    0.77
     Suite
    0.77
     Depot
    0.75
    mers
    0.70
    365
    0.69
     laundry
    0.68
     furniture
    0.67
    Activations Density 0.044%

    No Known Activations