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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 12399
    Prev
    Next
    INDEX
    Explanations

    references to computer programming terms related to caching and memory management

    oai_token-act-pair · gpt-3.5-turbo

    instances of the end of text markers or placeholders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.71
    emale
    -0.68
     Vaugh
    -0.67
     Franch
    -0.64
    enegger
    -0.63
     Ezek
    -0.62
     Hanson
    -0.60
     Byr
    -0.59
     Beir
    -0.59
     Gamble
    -0.58
    POSITIVE LOGITS
    ¶
    1.12
     parser
    1.04
    HTTP
    1.00
     filesystem
    1.00
    Python
    0.99
     HTTP
    0.99
     JSON
    0.98
     SQL
    0.97
     plugin
    0.95
    SQL
    0.95
    Activations Density 1.001%

    No Known Activations