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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13524
    Prev
    Next
    INDEX
    Explanations

    food-related terms, recipes, and ingredients

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to food and recipes

    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
    asio
    -0.83
    bably
    -0.80
     redacted
    -0.76
    canon
    -0.75
    putable
    -0.74
    anton
    -0.73
     parity
    -0.70
    alysed
    -0.70
    internet
    -0.69
    judicial
    -0.69
    POSITIVE LOGITS
     Kits
    1.13
     Powder
    1.13
     Coat
    1.07
     Style
    1.06
     Balls
    1.05
     Removal
    1.04
     Suite
    1.04
     Scale
    1.04
     Cups
    1.03
     Bars
    1.03
    Activations Density 0.320%

    No Known Activations