© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 11297
    Prev
    Next
    INDEX
    Explanations

    specific acronyms, likely related to companies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific energy company or entity denoted by "NR"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Metatron
    -0.73
    dates
    -0.72
    tumblr
    -0.68
    Minecraft
    -0.67
     Granger
    -0.64
    oise
    -0.63
    atchewan
    -0.63
     Villa
    -0.63
     Cthulhu
    -0.62
     undone
    -0.61
    POSITIVE LOGITS
     NR
    1.04
    NR
    0.87
    emonic
    0.87
    conservancy
    0.85
    otiation
    0.84
    rint
    0.84
     councill
    0.77
    yss
    0.76
    IGH
    0.73
    UTH
    0.73
    Activations Density 0.006%

    No Known Activations