Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 15020
    Prev
    Next
    INDEX
    Explanations

    dimensions and specifications related to technology products

    oai_token-act-pair · gpt-3.5-turbo

    specific technical specifications related to electronic devices, particularly dimensions and connectivity features

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

    No Comments

    Negative Logits
    kell
    -0.84
    mie
    -0.80
     Devon
    -0.75
    atl
    -0.74
    orkshire
    -0.72
    hoe
    -0.72
     largeDownload
    -0.71
    hower
    -0.71
    naire
    -0.68
     stew
    -0.68
    POSITIVE LOGITS
     GDDR
    1.09
     NVIDIA
    1.09
     PCIe
    1.08
    VIDIA
    1.05
     Lenovo
    1.02
     DDR
    1.00
     GPU
    0.99
     overcl
    0.99
     ASUS
    0.96
     PCI
    0.96
    Activations Density 0.331%

    No Known Activations