© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 18803
    Prev
    Next
    INDEX
    Explanations

    terms related to aerodynamics, especially with a focus on the word "aer"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to aerodynamics and aerospace engineering

    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
     Promise
    -0.73
    ources
    -0.68
     Pupp
    -0.68
     Continued
    -0.67
     Candy
    -0.65
     1886
    -0.65
     Todd
    -0.65
     Paw
    -0.64
    HI
    -0.64
     largeDownload
    -0.64
    POSITIVE LOGITS
    odynamic
    1.33
    odynam
    1.25
     aer
    1.17
    odynamics
    1.11
    obic
    1.04
     satell
    1.03
     advoc
    0.96
     destro
    0.95
     lapt
    0.90
    plane
    0.90
    Activations Density 0.006%

    No Known Activations