© 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. 13740
    Prev
    Next
    INDEX
    Explanations

    phrases related to baking and cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    cooking instructions and related actions

    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
     categ
    -0.72
    ody
    -0.71
     answers
    -0.65
     causation
    -0.65
     wiser
    -0.65
     persuasive
    -0.61
     endorsements
    -0.60
    etheless
    -0.60
     credible
    -0.59
    ozo
    -0.59
    POSITIVE LOGITS
     Pour
    1.21
     pour
    1.19
     sprinkle
    1.17
    Remove
    1.15
    Place
    1.11
    Heat
    1.06
     boil
    1.05
     Drain
    1.05
     Bake
    1.03
     Divide
    1.02
    Activations Density 0.085%

    No Known Activations