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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 10-RES-JB
    6. 9795
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions in recipes

    oai_token-act-pair · gpt-3.5-turbo

    cooking-related actions and ingredients

    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
     Jericho
    -0.71
     leased
    -0.68
     souven
    -0.66
     Aeg
    -0.66
     XD
    -0.65
     museums
    -0.65
    orthy
    -0.65
     rented
    -0.64
     rents
    -0.62
     Emblem
    -0.62
    POSITIVE LOGITS
     stirring
    1.12
     simmer
    1.05
     mixture
    1.02
     stir
    0.98
     Stir
    0.90
     blender
    0.90
     pulse
    0.87
     seasoning
    0.86
     stirred
    0.86
     teaspoon
    0.85
    Activations Density 0.086%

    No Known Activations