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. 10-RES-JB
    6. 19160
    Prev
    Next
    INDEX
    Explanations

    descriptors related to the physical characteristics and qualities of items

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives and phrases related to products and their qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enario
    -0.95
    imester
    -0.86
    ittee
    -0.82
    ablishment
    -0.82
    orah
    -0.81
    region
    -0.79
    artment
    -0.77
    ylum
    -0.77
    cosystem
    -0.73
    successful
    -0.73
    POSITIVE LOGITS
     goodies
    1.05
     herbs
    1.00
     towels
    0.97
     amounts
    0.94
     silicone
    0.94
     candles
    0.92
     spices
    0.92
     sunlight
    0.91
     charcoal
    0.90
     oils
    0.89
    Activations Density 0.315%

    No Known Activations