Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15723
    Prev
    Next
    INDEX
    Explanations

    relevant keywords and aspects in technical or instructional text

    oai_token-act-pair · gpt-3.5-turbo

    references to quantity and diversity in context

    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
    Brexit
    -0.80
    Pope
    -0.77
     Canaver
    -0.77
    Putin
    -0.76
     Lyndon
    -0.76
     Santorum
    -0.75
     Kremlin
    -0.75
     Croat
    -0.75
    Miami
    -0.74
    iola
    -0.74
    POSITIVE LOGITS
     functionality
    1.26
     items
    1.25
     entries
    1.23
     variables
    1.15
     configurations
    1.15
     settings
    1.12
     functions
    1.12
     contents
    1.11
     values
    1.09
     versions
    1.09
    Activations Density 0.543%

    No Known Activations