© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 21102
    Prev
    Next
    INDEX
    Explanations

    information related to recipes such as ingredients, preparation time, and serving sizes

    oai_token-act-pair · gpt-3.5-turbo

    information related to food recipes and their nutritional details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thereto
    -0.69
     tram
    -0.68
     outl
    -0.66
     diving
    -0.65
    dfx
    -0.64
     null
    -0.63
     evid
    -0.63
     EEG
    -0.62
    76561
    -0.60
     graphical
    -0.60
    POSITIVE LOGITS
    Ingredients
    1.19
     Ingredients
    1.09
    Recipe
    1.07
     Recipe
    1.03
    isine
    1.02
     Vegan
    0.90
    redients
    0.89
    Assembly
    0.89
    ritional
    0.88
    Method
    0.87
    Activations Density 0.136%

    No Known Activations