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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 15093
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent attacks and terrorism

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to attacks and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ãĤ´ãĥ³
    -0.86
    igmat
    -0.83
    dra
    -0.82
    ãĤ¦ãĤ¹
    -0.81
    catentry
    -0.80
    ripp
    -0.78
    ById
    -0.77
    ilk
    -0.77
    lost
    -0.74
    omaly
    -0.70
    POSITIVE LOGITS
     civilians
    1.18
     embassies
    1.17
     pedestrians
    1.11
     innocent
    1.09
     policemen
    1.08
     journalists
    1.05
     buses
    1.03
     unarmed
    1.02
     churches
    1.01
     mosques
    0.99
    Activations Density 0.197%

    No Known Activations