© 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. 9-RES-JB
    11. 1326
    Prev
    Next
    INDEX
    Explanations

    references to NSA surveillance activities and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the 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 @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.74
    hips
    -0.71
     Kard
    -0.69
     Kers
    -0.68
    âĵĺ
    -0.68
    fif
    -0.68
    ragon
    -0.66
    hani
    -0.65
    odge
    -0.65
    lihood
    -0.64
    POSITIVE LOGITS
     whistleblower
    1.18
    NSA
    1.13
     spying
    1.09
     surveillance
    0.95
     contractor
    0.92
     whistleblowers
    0.85
     Surveillance
    0.84
     spy
    0.83
    ionage
    0.81
     spies
    0.79
    Activations Density 0.039%

    No Known Activations