© 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. 12-RES-JB
    11. 3547
    Prev
    Next
    INDEX
    Explanations

    political and legal terms and situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to legal and political discussions surrounding intelligence and government actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.87
    Æ
    -0.85
    Magikarp
    -0.82
    NetMessage
    -0.80
    à¼
    -0.79
    coins
    -0.77
     masc
    -0.77
    æ©
    -0.77
    xual
    -0.76
    âĸ¬
    -0.75
    POSITIVE LOGITS
     Petraeus
    1.48
     declass
    1.31
     Cheney
    1.29
     CIA
    1.27
     Guant
    1.21
     Pentagon
    1.20
     inspector
    1.18
     Guantanamo
    1.17
     Inspector
    1.16
     Judicial
    1.14
    Activations Density 0.507%

    No Known Activations