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. 9-RES-JB
    6. 3931
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to physical violence and human rights violations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to severe violence and human rights abuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.80
    natureconservancy
    -0.78
     hindsight
    -0.74
     Investor
    -0.74
     Regulation
    -0.73
     predecessor
    -0.73
     disclaimer
    -0.73
     optimism
    -0.72
     Collider
    -0.72
    ãĤ´ãĥ³
    -0.72
    POSITIVE LOGITS
     raped
    1.06
     rapes
    1.05
     prostitutes
    1.01
     raping
    0.99
     indiscrim
    0.98
     rape
    0.93
     starvation
    0.90
     tortured
    0.90
     prisoners
    0.88
     corpses
    0.88
    Activations Density 0.484%

    No Known Activations