© 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. 7-RES-JB
    11. 7410
    Prev
    Next
    INDEX
    Explanations

    technology-related keywords like "fast," "portable," "solar," "powered," "decentralized," "educational," "open source," and "web security."

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to efficiency, affordability, and usability of products or technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lees
    -0.98
    doms
    -0.95
    pees
    -0.90
    clips
    -0.88
    akings
    -0.88
    Nazis
    -0.86
    kins
    -0.86
    idents
    -0.86
    aters
    -0.85
    rants
    -0.83
    POSITIVE LOGITS
     solution
    1.05
     alternative
    1.05
     tool
    1.01
     version
    1.01
     lightweight
    0.98
     reusable
    0.97
     example
    0.91
     standalone
    0.91
     resource
    0.91
     versatile
    0.90
    Activations Density 0.319%

    No Known Activations