© 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. 10-RES-JB
    11. 11454
    Prev
    Next
    INDEX
    Explanations

    words related to entrepreneurship and business, such as founder, marketing, and record

    oai_token-act-pair · gpt-3.5-turbo

    key individuals and their titles or roles in various projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ........
    -0.77
    fax
    -0.74
    ......
    -0.71
    ................
    -0.71
     ........
    -0.69
    ........................
    -0.69
     ..
    -0.69
    `.
    -0.69
    umbledore
    -0.67
    .....
    -0.67
    POSITIVE LOGITS
     indie
    1.07
     curated
    1.00
     NYU
    0.97
     Tumblr
    0.97
     filmmaker
    0.95
     TED
    0.94
     Indie
    0.94
     twent
    0.94
     BuzzFeed
    0.93
     Creative
    0.91
    Activations Density 0.665%

    No Known Activations