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. 16084
    Prev
    Next
    INDEX
    Explanations

    code-related terms and technology tools or platforms

    oai_token-act-pair · gpt-3.5-turbo

    references to programming languages and debugging tools

    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
     airing
    -0.76
     Noel
    -0.73
     totality
    -0.73
     striking
    -0.72
     Daly
    -0.72
     Rasmussen
    -0.71
     McCartney
    -0.70
     nationally
    -0.70
     afore
    -0.69
     airs
    -0.68
    POSITIVE LOGITS
    SQL
    1.27
    Config
    1.25
    Server
    1.24
    Install
    1.22
    Debug
    1.21
    Secure
    1.16
    Query
    1.14
    Desktop
    1.14
    Console
    1.14
    Client
    1.11
    Activations Density 0.320%

    No Known Activations