© 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. 3-RES-JB
    6. 7178
    Prev
    Next
    INDEX
    Explanations

    references to software version updates and technological platforms associated with Windows 10

    oai_token-act-pair · gpt-3.5-turbo

    references to Windows 10 and its related updates or features

    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
    href
    -0.84
    govtrack
    -0.83
    rahim
    -0.80
    actionDate
    -0.79
    Els
    -0.78
    owe
    -0.77
     mete
    -0.72
     sqor
    -0.72
     rab
    -0.71
    ãĥ´
    -0.71
    POSITIVE LOGITS
     desktop
    0.78
     Anniversary
    0.74
     Linux
    0.72
     Leopard
    0.72
    bourg
    0.72
     Desktop
    0.72
     MacBook
    0.70
    Ħ¢
    0.68
     kernels
    0.68
     laptops
    0.67
    Activations Density 0.044%

    No Known Activations