© 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. 12523
    Prev
    Next
    INDEX
    Explanations

    keywords related to computing and technology, specifically focusing on runtime functionalities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to programming and memory management

    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
    ongyang
    -0.98
    essee
    -0.86
    olulu
    -0.86
    hips
    -0.81
    Ĭ±
    -0.81
    ideon
    -0.80
    ushima
    -0.77
    ippi
    -0.76
    etsk
    -0.75
    berra
    -0.74
    POSITIVE LOGITS
     runtime
    0.96
     Runtime
    0.69
    fml
    0.68
    framework
    0.66
    UX
    0.63
    Exception
    0.63
     err
    0.63
     upkeep
    0.62
    belt
    0.60
     gad
    0.60
    Activations Density 0.012%

    No Known Activations