© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 21266
    Prev
    Next
    INDEX
    Explanations

    references to lighting candles

    oai_token-act-pair · gpt-3.5-turbo

    references to candles or related objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Introduced
    -0.64
     Genetics
    -0.62
     Gut
    -0.61
    doms
    -0.60
     Transit
    -0.58
     Geographic
    -0.58
     Obesity
    -0.57
     Overt
    -0.57
    ordan
    -0.57
     havoc
    -0.56
    POSITIVE LOGITS
     candle
    1.39
     Candle
    1.07
     candles
    1.05
    holder
    0.98
     lantern
    0.91
    lit
    0.88
    warm
    0.86
    pipe
    0.84
     exting
    0.83
    oshenko
    0.82
    Activations Density 0.009%

    No Known Activations