© 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. 4-RES-JB
    11. 18646
    Prev
    Next
    INDEX
    Explanations

    keywords related to light or lighting

    oai_token-act-pair · gpt-3.5-turbo

    references to "lights."

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

    No Comments

    Negative Logits
    llah
    -0.78
    urdue
    -0.67
    cture
    -0.66
    gress
    -0.66
    ordan
    -0.66
    ctive
    -0.65
    VD
    -0.65
     Rough
    -0.64
    arenthood
    -0.63
    >[
    -0.62
    POSITIVE LOGITS
     bulb
    1.06
     bulbs
    1.03
     lights
    1.00
    lights
    0.98
    pots
    0.96
     torches
    0.91
     shone
    0.91
     lamps
    0.90
     emitting
    0.90
     lantern
    0.88
    Activations Density 0.011%

    No Known Activations