Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7901
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to the sense of taste

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'taste'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.80
     Schne
    -0.69
     Cancel
    -0.69
     Lak
    -0.65
    chy
    -0.64
     Glob
    -0.63
     Kinnikuman
    -0.62
     ESA
    -0.62
    thus
    -0.61
     Grac
    -0.61
    POSITIVE LOGITS
     buds
    1.31
     tasting
    0.93
     tastes
    0.88
     palate
    0.88
     testers
    0.87
     taste
    0.86
     sensations
    0.82
     smelling
    0.81
     juices
    0.76
     tasted
    0.75
    Activations Density 0.017%

    No Known Activations