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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8403
    Prev
    Next
    INDEX
    Explanations

    phrases related to the National Security Agency (NSA) and its activities, especially spying

    oai_token-act-pair · gpt-3.5-turbo

    references to the NSA and its activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.82
    hips
    -0.74
    hani
    -0.70
    fif
    -0.70
    cause
    -0.69
    ragon
    -0.68
    odge
    -0.67
    uces
    -0.67
    lihood
    -0.66
     Camb
    -0.65
    POSITIVE LOGITS
     whistleblower
    1.06
     spying
    1.05
    NSA
    1.02
     surveillance
    0.94
     contractor
    0.90
    IDs
    0.86
     spy
    0.83
     spies
    0.79
     Surveillance
    0.78
     whistleblowers
    0.77
    Activations Density 0.033%

    No Known Activations