© 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. 8-RES-JB
    11. 1056
    Prev
    Next
    INDEX
    Explanations

    phrases related to protection and defense, especially of national interests and security

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with national security and protection

    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
    sonian
    -0.87
    Mode
    -0.69
    Mass
    -0.69
    cart
    -0.67
    SPONSORED
    -0.67
     guiActiveUnfocused
    -0.67
     NEWS
    -0.65
     reckoning
    -0.65
     describes
    -0.64
    HC
    -0.61
    POSITIVE LOGITS
     integrity
    1.09
     dignity
    1.06
     confidentiality
    1.02
     secrets
    0.97
     anonymity
    0.94
    icons
    0.93
    egu
    0.92
     indef
    0.91
     rights
    0.91
    yrights
    0.90
    Activations Density 0.185%

    No Known Activations