© 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. 3-RES-JB
    11. 586
    Prev
    Next
    INDEX
    Explanations

    instances of acronyms related to organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to organizational acronyms or abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saf
    -0.69
     Subjects
    -0.68
    ifications
    -0.68
     Hungarian
    -0.65
    ting
    -0.65
    lings
    -0.63
    icularly
    -0.63
    itarian
    -0.62
    lihood
    -0.62
     Danish
    -0.62
    POSITIVE LOGITS
    OPER
    1.01
    CO
    0.95
    verage
    0.94
    xon
    0.92
    KE
    0.91
    VER
    0.89
    CHR
    0.87
    ffee
    0.86
    VO
    0.85
    ptions
    0.84
    Activations Density 0.006%

    No Known Activations