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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12592
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to virtual machines

    oai_token-act-pair · gpt-3.5-turbo

    references to virtual machine technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alty
    -0.90
     Flavoring
    -0.82
     prevailing
    -0.81
    agher
    -0.79
    iflower
    -0.78
    alties
    -0.75
    ortment
    -0.73
    uten
    -0.73
    thritis
    -0.72
    baugh
    -0.71
    POSITIVE LOGITS
    kernel
    0.93
    VM
    0.92
    GPU
    0.90
    MC
    0.86
    DAQ
    0.86
    OST
    0.86
    ware
    0.83
    HS
    0.83
    Protect
    0.81
    Admin
    0.81
    Activations Density 0.019%

    No Known Activations