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. 11-RES-JB
    6. 19599
    Prev
    Next
    INDEX
    Explanations

    keywords related to virtual reality (VR) and associated devices such as Oculus Rift and Google Glass

    oai_token-act-pair · gpt-3.5-turbo

    references to virtual reality and augmented reality devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itri
    -0.85
    arial
    -0.76
     Byrd
    -0.75
    anches
    -0.71
     rhy
    -0.69
     Rollins
    -0.69
    istically
    -0.68
    amous
    -0.68
     Tripoli
    -0.68
    ten
    -0.66
    POSITIVE LOGITS
     headset
    1.30
     headsets
    1.14
     Rift
    1.08
     SDK
    1.04
     DK
    1.03
     headphones
    0.98
     wearer
    0.95
    XT
    0.95
     wearable
    0.95
    Lens
    0.91
    Activations Density 0.106%

    No Known Activations