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. 0-RES-JB
    6. 19760
    Prev
    Next
    INDEX
    Explanations

    terms related to burial places, specifically focusing on cemeteries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cemeteries and breweries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lead
    -0.78
    Ps
    -0.71
     Points
    -0.68
     Components
    -0.67
     Figures
    -0.67
     Cover
    -0.67
     Trey
    -0.66
     Ops
    -0.66
     Opt
    -0.66
     Frames
    -0.65
    POSITIVE LOGITS
     cemetery
    2.36
     monastery
    1.84
     cathedral
    1.84
     courthouse
    1.82
     bakery
    1.81
     chapel
    1.81
     synagogue
    1.77
     mosque
    1.77
     bookstore
    1.75
     brewery
    1.73
    Activations Density 0.041%

    No Known Activations