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

    Neuronpedia

    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. 11-RES-JB
    11. 7779
    Prev
    Next
    INDEX
    Explanations

    words related to laser technology

    oai_token-act-pair · gpt-3.5-turbo

    references to lasers and related technologies

    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
    illes
    -0.73
    ippi
    -0.71
     Mog
    -0.67
    itutional
    -0.66
     Rough
    -0.65
    skirts
    -0.65
    gres
    -0.64
     Territories
    -0.64
     Lynd
    -0.63
     Alive
    -0.63
    POSITIVE LOGITS
     beam
    1.23
    beam
    1.23
     beams
    1.10
     pointer
    1.08
     cutter
    1.04
    disc
    0.98
     projector
    0.98
     pointers
    0.95
     filament
    0.95
     scanner
    0.94
    Activations Density 0.065%

    No Known Activations