© 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. 15672
    Prev
    Next
    INDEX
    Explanations

    words related to oversight, audits, and investigations, particularly of governmental and organizational activities

    oai_token-act-pair · gpt-3.5-turbo

    references to oversight or regulatory bodies

    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
    udeau
    -0.81
    Population
    -0.74
     ç¥ŀ
    -0.72
    HAHAHAHA
    -0.66
    Attributes
    -0.66
    åĮ
    -0.65
    --+
    -0.65
    fly
    -0.65
     Warp
    -0.64
    Ped
    -0.64
    POSITIVE LOGITS
     probing
    1.31
     investigating
    1.29
     investigation
    1.12
     probe
    1.12
     watchdog
    1.10
     audit
    1.09
     investigator
    1.07
     inquiry
    1.05
    mbudsman
    1.04
     examining
    1.04
    Activations Density 0.169%

    No Known Activations