© 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. 0-RES-JB
    11. 5307
    Prev
    Next
    INDEX
    Explanations

    words related to lasers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of lasers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Account
    -0.80
     Couch
    -0.79
     Sum
    -0.78
     Unch
    -0.73
     Goodwin
    -0.73
    Sum
    -0.70
    adj
    -0.68
     Cherokee
    -0.67
    kj
    -0.67
    iety
    -0.67
    POSITIVE LOGITS
     laser
    3.53
     lasers
    3.09
     Laser
    2.82
     lightsaber
    1.40
     holog
    1.38
     LED
    1.34
     blaster
    1.33
     LEDs
    1.29
     beam
    1.27
     photon
    1.26
    Activations Density 0.014%

    No Known Activations