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

    Neuronpedia

    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. 7-RES-JB
    11. 3129
    Prev
    Next
    INDEX
    Explanations

    news or reports related to violent incidents resulting in casualties

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.83
     disclaimer
    -0.80
     caveat
    -0.71
     Advice
    -0.70
    soDeliveryDate
    -0.70
    Own
    -0.69
    cription
    -0.68
     Printed
    -0.67
     affirmation
    -0.66
     envy
    -0.64
    POSITIVE LOGITS
     innocent
    1.09
     civilians
    1.05
     bystanders
    0.89
     unarmed
    0.87
     innoc
    0.86
     pedestrians
    0.84
     hostages
    0.78
     victims
    0.77
     unsuspecting
    0.75
     occupants
    0.75
    Activations Density 0.117%

    No Known Activations