© 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 EvalsExportsAPI 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. 9-RES-JB
    11. 15863
    Prev
    Next
    INDEX
    Explanations

    phrases related to suspicion and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to suspicion or allegations of wrongdoing

    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
    00000
    -0.77
    patch
    -0.75
    Decre
    -0.72
    idge
    -0.70
    earch
    -0.70
    lite
    -0.70
    cms
    -0.69
    guy
    -0.69
    eries
    -0.69
     obser
    -0.68
    POSITIVE LOGITS
     terrorist
    1.09
     Islamist
    1.08
     paed
    1.08
     extremist
    1.02
     involvement
    1.00
     terrorists
    1.00
    arnaev
    0.99
     smuggling
    0.98
     terrorism
    0.98
     Osama
    0.98
    Activations Density 0.217%

    No Known Activations