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. 6-RES-JB
    6. 19308
    Prev
    Next
    INDEX
    Explanations

    mentions of specific groups of people, particularly citizens of different places

    oai_token-act-pair · gpt-3.5-turbo

    references to citizens or residents in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     certs
    -0.69
    attribute
    -0.69
    edi
    -0.68
    agi
    -0.67
     neurot
    -0.66
     handshake
    -0.66
    phabet
    -0.65
     continu
    -0.63
     thumbs
    -0.63
     projector
    -0.62
    POSITIVE LOGITS
     England
    0.96
     Janeiro
    0.96
     Philadelphia
    0.93
     Pennsylvania
    0.93
     Alexandria
    0.92
     Burlington
    0.92
    adelphia
    0.90
     Buenos
    0.90
     Plymouth
    0.90
     Ethiopia
    0.89
    Activations Density 0.121%

    No Known Activations