© 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. 0-RES-JB
    11. 18223
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Lisa" followed by a numerical value, possibly related to different contexts or mentions of a character named Lisa

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or entity, particularly names or acronyms related to a person or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wild
    -0.72
     trenches
    -0.66
     disposal
    -0.65
     dug
    -0.62
     barrel
    -0.62
     wheel
    -0.61
     folks
    -0.60
     table
    -0.60
     spiked
    -0.60
     nitrogen
    -0.59
    POSITIVE LOGITS
    isa
    4.56
    ISA
    2.42
    issa
    1.62
    ise
    1.43
    iza
    1.36
    isen
    1.28
    iso
    1.28
    esa
    1.25
    isi
    1.22
    ises
    1.18
    Activations Density 0.019%

    No Known Activations