© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 12210
    Prev
    Next
    INDEX
    Explanations

    violent actions related to law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    references to police actions and conflicts involving law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.95
    HCR
    -0.88
    alli
    -0.74
    HUD
    -0.73
     cured
    -0.73
     Surgery
    -0.72
    ortality
    -0.71
    otomy
    -0.71
    dinand
    -0.70
     absorbs
    -0.68
    POSITIVE LOGITS
     suspects
    1.23
     protesters
    1.16
     demonstrators
    1.15
     suspected
    1.14
     Occupy
    1.09
     suspect
    1.08
     protestors
    1.03
     suspicious
    1.02
     robbers
    1.01
     criminals
    0.97
    Activations Density 0.390%

    No Known Activations