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. 10-RES-JB
    6. 1711
    Prev
    Next
    INDEX
    Explanations

    mentions of borders, walls, and immigration-related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to border security and immigration policies

    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
    atre
    -0.80
    bet
    -0.80
     Olympus
    -0.79
     Shard
    -0.79
     Philips
    -0.78
     VK
    -0.78
    obyl
    -0.77
     Chess
    -0.76
     Nikon
    -0.76
    oult
    -0.76
    POSITIVE LOGITS
     deport
    1.96
     immigration
    1.90
     DACA
    1.85
     deportation
    1.85
     Immigration
    1.84
     deported
    1.81
     Mexicans
    1.80
     Mexican
    1.80
     undocumented
    1.80
     immigrants
    1.73
    Activations Density 0.568%

    No Known Activations