© 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. 6-RES-JB
    11. 2603
    Prev
    Next
    INDEX
    Explanations

    references to violent actions such as shootings and attacks

    oai_token-act-pair · gpt-3.5-turbo

    references to violent incidents or injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -1.05
    soDeliveryDate
    -0.90
    200000
    -0.85
    Companies
    -0.79
    Dialog
    -0.76
    WT
    -0.76
    lishes
    -0.76
    Wide
    -0.75
    âĶĢâĶĢâĶĢâĶĢ
    -0.74
     disclaimer
    -0.72
    POSITIVE LOGITS
     gunfire
    1.04
     unarmed
    0.81
     brutally
    0.80
     gunshot
    0.79
     bullets
    0.79
    angering
    0.77
     bombing
    0.76
     shootout
    0.76
     violently
    0.75
     gunshots
    0.75
    Activations Density 0.645%

    No Known Activations