© 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. 2279
    Prev
    Next
    INDEX
    Explanations

    terms related to efficiency, safety, and user-friendliness in processes and products

    oai_token-act-pair · gpt-3.5-turbo

    phrases that highlight efficiency, simplicity, and user-friendliness 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 @ 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
    mad
    -0.70
    polit
    -0.70
     hotly
    -0.68
    mir
    -0.66
    tre
    -0.65
    igion
    -0.65
    lis
    -0.64
    Muslim
    -0.62
     disl
    -0.61
     slander
    -0.61
    POSITIVE LOGITS
     workflow
    0.89
     efficient
    0.85
     streamlined
    0.84
    fficient
    0.83
     scalable
    0.83
     checkout
    0.78
     footprint
    0.78
     reusable
    0.78
     hassle
    0.77
     browsing
    0.76
    Activations Density 0.236%

    No Known Activations