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. 8849
    Prev
    Next
    INDEX
    Explanations

    references to virtual reality technology, specifically focusing on the Oculus Rift

    oai_token-act-pair · gpt-3.5-turbo

    references to virtual reality headsets, specifically the Oculus Rift

    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
     abbrevi
    -0.71
     Dodd
    -0.64
     Petr
    -0.63
     bonds
    -0.63
    living
    -0.61
    compl
    -0.60
    orpor
    -0.60
     PLAN
    -0.60
    cycles
    -0.59
    ARDS
    -0.59
    POSITIVE LOGITS
     DK
    1.04
     Rift
    0.99
     headset
    0.89
     Rivals
    0.86
    idge
    0.83
    borg
    0.79
    yip
    0.78
    izont
    0.75
    Lens
    0.75
     headsets
    0.75
    Activations Density 0.009%

    No Known Activations