Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 19634
    Prev
    Next
    INDEX
    Explanations

    terms related to law enforcement and political governance, including concepts like lawlessness, civil liberties, economic policy, and institutional protection

    oai_token-act-pair · gpt-3.5-turbo

    topics related to law enforcement and governance

    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
     Madison
    -0.91
     Lynch
    -0.88
    maxwell
    -0.86
     Everett
    -0.84
     Byrd
    -0.83
     Garfield
    -0.83
     Omaha
    -0.80
     Amtrak
    -0.79
     Indiana
    -0.78
     Edmund
    -0.78
    POSITIVE LOGITS
     Kazakh
    1.06
     Azerbai
    0.95
     Houth
    0.95
     Jihad
    0.94
     Iranians
    0.90
     PKK
    0.90
    zbollah
    0.89
     Syrians
    0.86
     Azerbaijan
    0.86
     YPG
    0.86
    Activations Density 0.669%

    No Known Activations