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. 21330
    Prev
    Next
    INDEX
    Explanations

    descriptions of making or creating something

    oai_token-act-pair · gpt-3.5-turbo

    instructional content related to crafting or DIY projects

    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
    advertising
    -0.88
    iberal
    -0.83
     antitrust
    -0.78
    sych
    -0.73
    reporting
    -0.73
     abst
    -0.72
     intoxication
    -0.72
    inventoryQuantity
    -0.71
     dementia
    -0.70
     Venezuel
    -0.70
    POSITIVE LOGITS
    Materials
    1.22
     schematic
    1.13
     textures
    1.09
     sketches
    1.08
     drawings
    1.07
     STL
    1.06
     diagrams
    1.05
     Sketch
    1.03
     PVC
    1.03
    Assembly
    1.02
    Activations Density 0.840%

    No Known Activations