© 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. 9-RES-JB
    11. 1896
    Prev
    Next
    INDEX
    Explanations

    mentions of the CIA

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "CIA"

    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
    ghai
    -0.78
     Mulcair
    -0.74
    kj
    -0.73
    nings
    -0.73
    kees
    -0.73
    steen
    -0.72
    igans
    -0.71
     Leafs
    -0.70
    ths
    -0.68
     Qué
    -0.68
    POSITIVE LOGITS
     annex
    1.01
     Director
    0.92
    andestine
    0.90
     operatives
    0.87
     Headquarters
    0.84
    CIA
    0.82
     covert
    0.82
     headquarters
    0.81
     operative
    0.80
     counterterrorism
    0.79
    Activations Density 0.041%

    No Known Activations