© 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. 2-RES-JB
    11. 12767
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of storing information or energy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data storage

    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
    eda
    -0.70
    edly
    -0.69
    eds
    -0.69
    gui
    -0.67
    eded
    -0.66
    alities
    -0.65
    isms
    -0.62
    sky
    -0.61
    nel
    -0.60
    aldi
    -0.59
    POSITIVE LOGITS
     storing
    1.00
     stored
    0.89
    ãĤ´
    0.88
    ograp
    0.83
     veter
    0.81
    mosp
    0.78
     calories
    0.77
     toget
    0.77
    ãĤª
    0.76
    Store
    0.76
    Activations Density 0.017%

    No Known Activations