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. 11-RES-JB
    6. 3227
    Prev
    Next
    INDEX
    Explanations

    words related to different cultures, ethnicities, and historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to different groups of people and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    inventoryQuantity
    -0.99
     deadlines
    -0.71
    PORT
    -0.71
    paren
    -0.71
     showc
    -0.70
    bernatorial
    -0.69
     deadline
    -0.66
    Sales
    -0.66
     announcements
    -0.65
     lasers
    -0.65
    POSITIVE LOGITS
     whom
    1.27
     inhab
    1.24
     worshipped
    1.16
     residing
    1.15
     enslaved
    1.11
     who
    1.10
     descended
    1.06
     inhabited
    1.06
    who
    1.05
     belonging
    1.03
    Activations Density 0.414%

    No Known Activations