© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 2185
    Prev
    Next
    INDEX
    Explanations

    words related to intelligence agencies and committees

    oai_token-act-pair · gpt-3.5-turbo

    references to intelligence agencies and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zl
    -0.75
    interstitial
    -0.72
    emp
    -0.71
    anan
    -0.70
    haw
    -0.70
    loading
    -0.68
    yards
    -0.68
    unin
    -0.67
    artifacts
    -0.66
     unreal
    -0.65
    POSITIVE LOGITS
     Agency
    1.00
     Bureau
    0.91
     Surveillance
    0.87
     Committee
    0.80
     Intelligence
    0.80
    elligence
    0.79
    atform
    0.78
     Authorization
    0.76
     Oversight
    0.75
    iator
    0.75
    Activations Density 0.024%

    No Known Activations