© 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. 11209
    Prev
    Next
    INDEX
    Explanations

    references to vegetables

    oai_token-act-pair · gpt-3.5-turbo

    mentions of vegetables

    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
    ospace
    -0.77
    dinand
    -0.75
    76561
    -0.72
    raints
    -0.72
    ircraft
    -0.71
    ancers
    -0.69
    Oracle
    -0.68
    antasy
    -0.67
    DOS
    -0.67
    eatures
    -0.67
    POSITIVE LOGITS
     salad
    1.31
     salads
    1.24
     vegetables
    1.14
     peel
    1.10
     soup
    1.08
     vegetable
    1.07
     Salad
    1.07
     cabbage
    1.04
     juice
    1.04
     fries
    1.02
    Activations Density 0.045%

    No Known Activations