© 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. 11-RES-JB
    11. 10251
    Prev
    Next
    INDEX
    Explanations

    cooking instructions involving specific actions and ingredients

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to cooking methods and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xus
    -0.74
    女
    -0.72
     guiActiveUn
    -0.69
    oho
    -0.66
     Geographic
    -0.64
    ledged
    -0.64
    zig
    -0.62
     acknowled
    -0.61
     Regulatory
    -0.60
     stride
    -0.60
    POSITIVE LOGITS
     onions
    1.24
     rice
    1.22
     potatoes
    1.18
     veggies
    1.14
     vegetables
    1.12
     tofu
    1.10
     chicken
    1.09
     beans
    1.08
     shrimp
    1.06
     meats
    1.05
    Activations Density 0.078%

    No Known Activations