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. 11-RES-JB
    6. 3031
    Prev
    Next
    INDEX
    Explanations

    complex technical terms and phrases relating to software development

    oai_token-act-pair · gpt-3.5-turbo

    references to efficiency and convenience in processes or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rasmussen
    -0.93
    south
    -0.81
     Malk
    -0.80
     Reeves
    -0.78
     Brock
    -0.75
     Patt
    -0.74
     Shots
    -0.72
    Pitt
    -0.72
    Cele
    -0.72
     POLITICO
    -0.71
    POSITIVE LOGITS
     comput
    1.28
     synt
    1.26
     syntax
    1.26
     abstraction
    1.23
     inefficient
    1.23
     interoper
    1.21
     usability
    1.17
     idi
    1.16
     cumbersome
    1.16
     boiler
    1.16
    Activations Density 0.327%

    No Known Activations