Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 4073
    Prev
    Next
    INDEX
    Explanations

    terms related to government surveillance and intelligence agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental surveillance and intelligence programs

    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
     Wrest
    -0.84
    ciation
    -0.79
     Dise
    -0.77
     Converted
    -0.76
    rition
    -0.75
     Kinn
    -0.75
    Unity
    -0.75
     Wheels
    -0.74
     relegation
    -0.74
     Sadd
    -0.73
    POSITIVE LOGITS
     NSA
    1.88
     surveillance
    1.85
     spying
    1.84
    NSA
    1.79
     Surveillance
    1.73
     FISA
    1.67
     eaves
    1.65
     wiret
    1.64
    illance
    1.63
    Privacy
    1.52
    Activations Density 0.840%

    No Known Activations