© 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. 10-RES-JB
    11. 13635
    Prev
    Next
    INDEX
    Explanations

    phrases related to cooking and food preparation

    oai_token-act-pair · gpt-3.5-turbo

    instructions or recommendations related to cooking and food preparation

    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
    Privacy
    -0.94
    iannopoulos
    -0.83
    yrights
    -0.80
    reply
    -0.78
     careers
    -0.76
    ERROR
    -0.74
    Reilly
    -0.74
    LOS
    -0.73
    CLASSIFIED
    -0.73
    Politics
    -0.72
    POSITIVE LOGITS
     powdered
    1.41
     coconut
    1.31
     dried
    1.29
     almonds
    1.28
     vinegar
    1.27
     olive
    1.27
     oats
    1.27
     distilled
    1.25
     almond
    1.25
     herbs
    1.23
    Activations Density 0.215%

    No Known Activations