© 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. 10186
    Prev
    Next
    INDEX
    Explanations

    law enforcement and security-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement and police presence

    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
    ulent
    -0.70
    ebted
    -0.69
     Prophe
    -0.68
     Decay
    -0.68
     Madness
    -0.68
    aldehyde
    -0.67
     regrets
    -0.65
    ;;;;;;;;;;;;
    -0.65
     Invention
    -0.64
    stories
    -0.64
    POSITIVE LOGITS
     patrolling
    1.46
     patrol
    1.38
     stationed
    1.33
     patrols
    1.31
     escorted
    1.28
     helicop
    1.24
     escort
    1.21
     swoop
    1.18
     raided
    1.17
     intervened
    1.17
    Activations Density 0.271%

    No Known Activations