© 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. 3-RES-JB
    11. 23896
    Prev
    Next
    INDEX
    Explanations

    details of criminal incidents or law enforcement activities

    oai_token-act-pair · gpt-3.5-turbo

    events or incidents related to crime and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ç¥ŀ
    -0.89
    çļ
    -0.81
     prag
    -0.73
     philosophers
    -0.73
     Centauri
    -0.72
    DragonMagazine
    -0.68
     Protoss
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
     ãĤµ
    -0.65
    asury
    -0.65
    POSITIVE LOGITS
     police
    0.95
     RCMP
    0.92
     assailant
    0.92
     assailants
    0.91
     suspected
    0.90
     unidentified
    0.90
     altercation
    0.89
     NYPD
    0.89
     sheriff
    0.88
     LAPD
    0.87
    Activations Density 1.904%

    No Known Activations