© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 2679
    Prev
    Next
    INDEX
    Explanations

    cooking instructions and recipe details, particularly those related to spiciness and flavor enhancement

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and symbols that convey excitement or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hannity
    -0.74
     advers
    -0.74
     echoing
    -0.74
     affiliated
    -0.71
     Orwell
    -0.71
     organis
    -0.71
     estranged
    -0.71
     synd
    -0.70
     affirmative
    -0.70
     Wikileaks
    -0.70
    POSITIVE LOGITS
    Ingredients
    1.38
    Recipe
    1.23
    Recommended
    1.04
    Remove
    1.02
    Step
    1.00
    Instruct
    0.99
    ³³³³³³³³³³³³³³³³
    0.98
    Finish
    0.94
    Heat
    0.94
    Product
    0.94
    Activations Density 0.311%

    No Known Activations