© 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. 3-RES-JB
    11. 1921
    Prev
    Next
    INDEX
    Explanations

    terms related to spices and their usage, particularly in culinary or health contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to various spices

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cedented
    -0.86
    apsed
    -0.77
    isner
    -0.74
    ffen
    -0.74
    avering
    -0.73
    vernment
    -0.72
    ufact
    -0.72
    phis
    -0.71
     Turing
    -0.69
    elong
    -0.68
    POSITIVE LOGITS
     spice
    1.18
     blends
    1.02
     spices
    1.00
     powd
    0.93
     blend
    0.87
     seasoning
    0.87
     Spice
    0.80
     flav
    0.79
     latt
    0.78
    bean
    0.78
    Activations Density 0.008%

    No Known Activations