© 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. 0-RES-JB
    11. 5143
    Prev
    Next
    INDEX
    Explanations

    references to the brand "Nutella."

    oai_token-act-pair · gpt-3.5-turbo

    references to Nutella or its associated themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cc
    -0.74
     pistols
    -0.70
     cruiser
    -0.70
     que
    -0.69
     pistol
    -0.69
     partial
    -0.67
    >[
    -0.65
     laz
    -0.64
    arios
    -0.64
     superpower
    -0.64
    POSITIVE LOGITS
     Nut
    3.94
    Nut
    2.37
    nut
    1.59
     Nutrition
    1.49
     nutrient
    1.26
    nuts
    1.18
     Nig
    1.18
     Om
    1.16
     Ster
    1.16
     nutrients
    1.13
    Activations Density 0.018%

    No Known Activations