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. 12-RES-JB
    6. 14567
    Prev
    Next
    INDEX
    Explanations

    information related to lighting, including mentions of lights going up, dimming, brightening, being off, or specific types of lights like LED lights

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to various types of lights and lighting situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    culosis
    -0.84
    xit
    -0.76
    llah
    -0.72
    ilage
    -0.72
     Bundy
    -0.72
    nia
    -0.67
    gey
    -0.66
     Bagg
    -0.66
     Mellon
    -0.64
    utsche
    -0.63
    POSITIVE LOGITS
     bulbs
    1.32
     illuminating
    1.29
     bulb
    1.29
    bul
    1.21
     illuminate
    1.17
     fixtures
    1.09
     flickering
    1.05
     shining
    1.03
     fixture
    1.03
     blinking
    1.03
    Activations Density 0.107%

    No Known Activations