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. 8-RES-JB
    6. 18268
    Prev
    Next
    INDEX
    Explanations

    words related to specific ethnic and religious groups

    oai_token-act-pair · gpt-3.5-turbo

    references to specific national or ethnic identities, particularly focusing on Muslims, Palestinians, and Americans

    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
    ologies
    -1.04
    abilities
    -0.94
    ories
    -0.88
    arters
    -0.87
    sections
    -0.87
    rings
    -0.85
    ravings
    -0.85
    irens
    -0.84
     suites
    -0.84
    events
    -0.84
    POSITIVE LOGITS
     citizen
    1.08
     woman
    1.04
     politician
    1.04
     colleague
    1.02
     journalist
    1.00
     who
    1.00
     diplomat
    0.99
     teenager
    0.98
     businessman
    0.95
     prostitute
    0.95
    Activations Density 0.215%

    No Known Activations