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. 7-RES-JB
    6. 5814
    Prev
    Next
    INDEX
    Explanations

    references to virtual reality headsets, specifically Oculus Rift, and related information

    oai_token-act-pair · gpt-3.5-turbo

    references to the Oculus Rift virtual reality headset

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rollins
    -0.67
     delinqu
    -0.67
    theless
    -0.64
    othy
    -0.63
     iod
    -0.62
    coat
    -0.62
    phrase
    -0.61
     spelling
    -0.60
     reconc
    -0.60
    akuya
    -0.60
    POSITIVE LOGITS
     Rift
    1.38
     Oculus
    0.92
     headset
    0.91
     DK
    0.91
    XT
    0.88
    asonic
    0.85
    Lens
    0.83
     headsets
    0.77
    ï¸
    0.77
     VR
    0.77
    Activations Density 0.027%

    No Known Activations