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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13436
    Prev
    Next
    INDEX
    Explanations

    mentions of the NSA (National Security Agency)

    oai_token-act-pair · gpt-3.5-turbo

    references to the National Security Agency (NSA) and its surveillance activities

    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
    interstitial
    -0.75
    lihood
    -0.72
    âĵĺ
    -0.72
    iston
    -0.71
     Kers
    -0.70
    hips
    -0.68
    uces
    -0.68
    nutrition
    -0.67
    odge
    -0.66
    Brew
    -0.66
    POSITIVE LOGITS
     whistleblower
    1.17
     spying
    1.11
    NSA
    1.11
     surveillance
    1.06
     contractor
    0.95
     Surveillance
    0.94
     spy
    0.88
     spies
    0.86
     NSA
    0.86
     whistleblowers
    0.85
    Activations Density 0.039%

    No Known Activations