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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 4985
    Prev
    Next
    INDEX
    Explanations

    phrases related to government surveillance and data collection

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government surveillance and data collection practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hus
    -0.67
    HY
    -0.65
    oba
    -0.64
     Slug
    -0.63
     Temper
    -0.62
    reci
    -0.62
     Conquer
    -0.61
     Chrys
    -0.61
     Bie
    -0.60
     Flav
    -0.60
    POSITIVE LOGITS
     spying
    1.23
     surveillance
    1.12
    ionage
    1.12
     wiret
    1.00
    NSA
    0.96
     eaves
    0.96
    illance
    0.95
     targeting
    0.92
     interceptions
    0.90
     NSA
    0.90
    Activations Density 0.202%

    No Known Activations