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. 15077
    Prev
    Next
    INDEX
    Explanations

    mentions of immigration-related terms or policies

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

    terms related to immigration and immigrant status

    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
    idges
    -0.81
    lain
    -0.81
    ovember
    -0.80
    rov
    -0.77
    é¾
    -0.75
    apter
    -0.75
    ivable
    -0.74
    ival
    -0.74
    ategory
    -0.73
    isites
    -0.71
    POSITIVE LOGITS
     detention
    0.99
     laborers
    0.97
     deported
    0.96
     immigrants
    0.93
     deportation
    0.87
     Guatem
    0.87
     immigrant
    0.87
     visas
    0.84
     deport
    0.82
     labou
    0.82
    Activations Density 0.064%

    No Known Activations