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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3263
    Prev
    Next
    INDEX
    Explanations

    references to the HTC Vive virtual reality headset

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Vive" headset and related consumer electronics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swick
    -0.76
     Applicant
    -0.70
     dated
    -0.65
     abbrevi
    -0.65
    alez
    -0.64
    ciating
    -0.64
     acronym
    -0.63
    talking
    -0.62
     Cosponsors
    -0.62
    aceous
    -0.61
    POSITIVE LOGITS
     Vive
    1.22
    pheus
    0.85
    heed
    0.84
    yip
    0.75
    awei
    0.72
     aback
    0.71
     horr
    0.70
    idia
    0.70
    tsky
    0.69
    ptions
    0.69
    Activations Density 0.008%

    No Known Activations