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. 209
    Prev
    Next
    INDEX
    Explanations

    topics related to social issues and policies, such as climate change, marijuana legalization, healthcare, and housing rights

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social issues and environmental concerns

    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
    20439
    -0.63
     haha
    -0.58
     guiActiveUnfocused
    -0.58
    berra
    -0.57
     ..."
    -0.55
    ./
    -0.55
    obe
    -0.55
    lain
    -0.54
     ......
    -0.54
    ads
    -0.53
    POSITIVE LOGITS
     advocates
    0.64
     proponents
    0.62
     stakeholders
    0.61
     procurement
    0.60
     lawy
    0.59
     enthusiasts
    0.56
    gate
    0.55
     suppliers
    0.54
     Advisory
    0.54
     historian
    0.54
    Activations Density 0.804%

    No Known Activations