© 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. 10-RES-JB
    11. 11319
    Prev
    Next
    INDEX
    Explanations

    phrases related to police activities and crime scenes

    oai_token-act-pair · gpt-3.5-turbo

    locations and addresses within events or incidents

    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
     extinct
    -0.78
     boycot
    -0.77
    etheless
    -0.76
    joice
    -0.76
     crore
    -0.71
     humili
    -0.70
     deserves
    -0.70
     hitherto
    -0.70
     fortnight
    -0.69
    lihood
    -0.69
    POSITIVE LOGITS
    Officers
    1.50
     Officers
    1.28
     officers
    1.18
    Police
    1.13
     deputies
    1.07
    Investigators
    1.05
     troopers
    1.04
    Upon
    1.00
    EMS
    0.99
     Investigators
    0.99
    Activations Density 0.277%

    No Known Activations