© 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. 15541
    Prev
    Next
    INDEX
    Explanations

    words related to various substances, especially those associated with flavors or textures, like sugar, water, frost, dust, acid, lime, avocado, ice cream, and plasma

    oai_token-act-pair · gpt-3.5-turbo

    references to various food-related substances and ingredients

    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
    ItemImage
    -0.86
    Introduced
    -0.78
    HCR
    -0.77
    Ĭ±
    -0.76
     Iter
    -0.75
    Ability
    -0.74
     Proceedings
    -0.73
     [|
    -0.73
     Directions
    -0.72
     Entry
    -0.71
    POSITIVE LOGITS
    bag
    1.03
    boxing
    1.02
     daddy
    0.99
    boarding
    0.98
    bending
    0.96
    haired
    0.95
     bikini
    0.93
    ball
    0.92
    iest
    0.92
    box
    0.91
    Activations Density 0.349%

    No Known Activations