Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 17813
    Prev
    Next
    INDEX
    Explanations

    descriptions of processes, actions, and developments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    aspects related to real estate transactions and market conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ
    -1.12
     âĢ
    -1.03
    âĢł
    -0.85
    ¨
    -0.84
    âī
    -0.71
    ãĢį
    -0.70
     MORE
    -0.70
    âĻ
    -0.69
    ":["
    -0.69
     Lastly
    -0.69
    POSITIVE LOGITS
     crowdfunding
    0.95
     DIY
    0.93
     fledgling
    0.89
    reprene
    0.88
     entrepreneurial
    0.87
     entrepreneurship
    0.82
     Craigslist
    0.81
     brainstorm
    0.81
     startup
    0.80
     venture
    0.77
    Activations Density 1.082%

    No Known Activations