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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 224
    Prev
    Next
    INDEX
    Explanations

    phrases related to various specific areas of professional focus, such as farming, gambling, gaming, climate change, cycling, humanitarian aid, astronomy, marijuana legalization, physics, bitcoin mining, doping culture, rights, investment management, conservation, science, money laundering, transportation

    oai_token-act-pair · gpt-3.5-turbo

    topics related to various social, environmental, and industry issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alin
    -0.75
    olen
    -0.68
    Lago
    -0.66
    annis
    -0.66
    sudo
    -0.66
     alike
    -0.65
    awatts
    -0.64
    ridges
    -0.64
    Downloadha
    -0.63
    dain
    -0.63
    POSITIVE LOGITS
     bureau
    1.03
     community
    0.99
     department
    0.98
     industry
    0.97
     playbook
    0.97
     program
    0.95
     equation
    0.95
     ecosystem
    0.94
     landscape
    0.93
     situation
    0.93
    Activations Density 0.576%

    No Known Activations