© 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. 10-RES-JB
    11. 16943
    Prev
    Next
    INDEX
    Explanations

    phrases related to incidents involving law enforcement, accidents, and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    incidents involving death or serious injuries

    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
    izons
    -0.99
    osponsors
    -0.96
    ographies
    -0.81
     scholars
    -0.81
    AppData
    -0.78
     trillions
    -0.74
    ometers
    -0.73
     guides
    -0.73
     ç¥ŀ
    -0.72
     historians
    -0.72
    POSITIVE LOGITS
     altercation
    1.64
     incident
    1.46
     robbery
    1.38
     brawl
    1.32
     shootout
    1.30
     disturbance
    1.28
     confrontation
    1.28
     stabbing
    1.26
     attack
    1.25
     collision
    1.25
    Activations Density 0.307%

    No Known Activations