© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 6736
    Prev
    Next
    INDEX
    Explanations

    specific technology-related terms, particularly related to virtual reality devices like "Vive" and "Switch"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Vive virtual reality headset

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swick
    -0.70
     Bermuda
    -0.69
    ciating
    -0.67
     abbrevi
    -0.66
    alez
    -0.65
    aceous
    -0.65
    istics
    -0.64
    ymes
    -0.64
    odes
    -0.63
     Applicant
    -0.63
    POSITIVE LOGITS
     Vive
    1.16
    yip
    0.90
    pheus
    0.77
    heed
    0.77
     aback
    0.76
    ptions
    0.76
    gging
    0.72
    lette
    0.72
    phas
    0.70
    rers
    0.70
    Activations Density 0.006%

    No Known Activations