© 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. 11229
    Prev
    Next
    INDEX
    Explanations

    words related to lighting

    oai_token-act-pair · gpt-3.5-turbo

    references to lighting conditions and effects

    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
    sburgh
    -0.85
    berus
    -0.80
    clair
    -0.78
    irlf
    -0.76
    remlin
    -0.76
    ilage
    -0.74
    apego
    -0.74
    essor
    -0.73
    gres
    -0.68
    Ô
    -0.68
    POSITIVE LOGITS
     torches
    1.12
     lighting
    1.07
     bulbs
    0.99
     fixtures
    0.98
     bulb
    0.97
     lamps
    0.96
     candles
    0.95
    lights
    0.89
     fixture
    0.86
     lights
    0.85
    Activations Density 0.010%

    No Known Activations