Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 1782
    Prev
    Next
    INDEX
    Explanations

    references to specific nationalities, particularly Chinese nationals

    oai_token-act-pair · gpt-3.5-turbo

    references to various nationalities and citizenship status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Oracle
    -0.70
     Churchill
    -0.68
    nce
    -0.67
    MENT
    -0.67
    Station
    -0.66
    AST
    -0.66
     Canary
    -0.65
    âĶĢâĶĢ
    -0.64
    rol
    -0.64
    Stretch
    -0.64
    POSITIVE LOGITS
     nationals
    1.34
    doms
    0.93
    ecided
    0.90
     versa
    0.86
    apons
    0.86
     citiz
    0.84
    ignty
    0.83
    mares
    0.83
    iversal
    0.81
     abroad
    0.80
    Activations Density 0.008%

    No Known Activations