© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 3155
    Prev
    Next
    INDEX
    Explanations

    phrases related to immigration policies and border control

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to immigration restrictions and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.72
    åħī
    -0.72
    rag
    -0.71
    ç·
    -0.69
    peer
    -0.69
    ãĤ´
    -0.68
    orsche
    -0.67
    ointed
    -0.67
    é¾
    -0.67
    letter
    -0.67
    POSITIVE LOGITS
     mainland
    0.99
     countries
    0.96
     America
    0.95
     illegally
    0.94
     Britain
    0.93
     Australia
    0.89
     shores
    0.89
     Countries
    0.88
     cities
    0.87
     democracies
    0.87
    Activations Density 0.277%

    No Known Activations