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. 10-RES-JB
    6. 163
    Prev
    Next
    INDEX
    Explanations

    aspects related to technological devices, including design, finish, execution, and quality

    oai_token-act-pair · gpt-3.5-turbo

    elements related to the quality and production of films or media

    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
    Dispatch
    -0.72
    iatus
    -0.68
    ELF
    -0.67
    ighed
    -0.67
    emonic
    -0.67
    20439
    -0.66
    icer
    -0.66
    otonin
    -0.65
    ģĸ
    -0.65
    RAG
    -0.64
    POSITIVE LOGITS
     varies
    1.08
     aspect
    0.99
     feels
    0.99
     reminds
    0.96
     sucks
    0.94
     isn
    0.91
     seems
    0.90
     quirks
    0.90
     resembles
    0.88
     revolves
    0.87
    Activations Density 0.334%

    No Known Activations