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. 15195
    Prev
    Next
    INDEX
    Explanations

    phrases related to immigration and politics, particularly regarding specific actions, policies, and individuals

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

    phrases related to immigration and entry into the United States

    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
    Dispatch
    -0.74
    Ò
    -0.68
    arians
    -0.66
    eers
    -0.65
    ................................................................
    -0.62
    rification
    -0.60
    Rs
    -0.59
    Timeout
    -0.59
    -+-+-+-+
    -0.59
    Handler
    -0.59
    POSITIVE LOGITS
     United
    1.40
     country
    1.26
     U
    1.11
    United
    1.08
     US
    1.06
     USA
    1.03
     continental
    1.02
     UNITED
    1.01
     contiguous
    1.01
     Americas
    0.90
    Activations Density 0.107%

    No Known Activations