© 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. 10678
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversy or criticism

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a state of pressure or scrutiny

    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
     Begins
    -0.75
    ibia
    -0.65
     Retrieved
    -0.65
     Papers
    -0.64
     Mermaid
    -0.64
    nesday
    -0.62
    VG
    -0.62
     Recipes
    -0.62
     Trib
    -0.61
     Started
    -0.61
    POSITIVE LOGITS
     pressure
    1.25
     scrutiny
    1.15
    whel
    1.08
    staff
    1.02
     siege
    1.02
    dogs
    1.01
    pressure
    1.00
    powered
    0.99
     threat
    0.97
     intense
    0.93
    Activations Density 0.042%

    No Known Activations