© 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. 7-RES-JB
    11. 11350
    Prev
    Next
    INDEX
    Explanations

    phrases related to being under pressure or under investigation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "under" in various contexts indicating pressure, investigation, or ongoing issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Begins
    -0.73
     Glob
    -0.62
     Tek
    -0.62
     VIDEOS
    -0.62
     Papers
    -0.60
    Tur
    -0.58
     rob
    -0.58
    acular
    -0.58
     sake
    -0.57
     ancestor
    -0.57
    POSITIVE LOGITS
    valued
    1.12
    lined
    1.06
    whel
    1.02
    whelming
    1.02
    powered
    1.02
    developed
    1.01
    written
    0.98
    stood
    0.97
    represented
    0.97
    pins
    0.96
    Activations Density 0.039%

    No Known Activations