© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16062
    Prev
    Next
    INDEX
    Explanations

    mention of caching mechanisms and related technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to computer science concepts and terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Byr
    -0.61
     Reeves
    -0.61
     Oliv
    -0.60
     Ezek
    -0.60
     Hanson
    -0.60
     Paula
    -0.60
     Bravo
    -0.59
     Euros
    -0.59
     Bust
    -0.59
     Vaugh
    -0.58
    POSITIVE LOGITS
    ¶
    1.18
     HTTP
    1.10
     namespace
    1.06
     parser
    1.06
     initialization
    1.04
     JSON
    1.03
    HTTP
    1.02
     filesystem
    1.01
     statically
    1.01
     async
    1.01
    Activations Density 0.680%

    No Known Activations