© 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. 9-RES-JB
    11. 17503
    Prev
    Next
    INDEX
    Explanations

    recipes or cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    ingredient measurements and cooking instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fielded
    -0.79
     careers
    -0.71
     frequ
    -0.71
     evolved
    -0.70
     veter
    -0.68
    ¥µ
    -0.68
     benef
    -0.66
     Ranking
    -0.66
     EB
    -0.66
     foreseeable
    -0.65
    POSITIVE LOGITS
    Instruct
    1.23
    ½
    1.21
    Salt
    1.14
    Method
    1.13
    Ingredients
    1.12
    Direct
    1.12
     teaspoon
    1.03
    Recipe
    1.03
     tablespoon
    1.02
    egg
    1.02
    Activations Density 0.044%

    No Known Activations