© 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 EvalsExportsinterp-engineNEWAPI 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. 14542
    Prev
    Next
    INDEX
    Explanations

    words related to international politics and military affairs

    oai_token-act-pair · gpt-3.5-turbo

    references to US-led military actions and policies

    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
     beads
    -0.74
     Meadows
    -0.73
     Aval
    -0.70
     coefficients
    -0.69
     happ
    -0.69
     springs
    -0.68
     coefficient
    -0.68
     Ell
    -0.68
     headlights
    -0.68
     Leaf
    -0.67
    POSITIVE LOGITS
    controlled
    1.37
    induced
    1.35
    sponsored
    1.35
    administ
    1.33
    dominated
    1.31
    backed
    1.30
    approved
    1.29
    owned
    1.26
    imposed
    1.24
    affiliated
    1.24
    Activations Density 0.091%

    No Known Activations