© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 16388
    Prev
    Next
    INDEX
    Explanations

    references to surveillance and wiretapping activities by authorities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to surveillance and wiretapping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mankind
    -0.80
     Human
    -0.71
     Anthrop
    -0.68
    Urban
    -0.66
     VAT
    -0.66
    Metro
    -0.66
     Virgin
    -0.65
    ³³³³³³³³
    -0.65
    anza
    -0.65
     FAT
    -0.64
    POSITIVE LOGITS
     wiret
    1.18
     eaves
    1.00
     helic
    1.00
    kefeller
    0.95
    apped
    0.90
    apping
    0.88
    apper
    0.87
    apons
    0.87
     ank
    0.86
    appers
    0.83
    Activations Density 0.008%

    No Known Activations