© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4025
    Prev
    Next
    INDEX
    Explanations

    details of criminal activities, such as robberies and attempted robberies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to personal items, electronics, and information related to theft or robbery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ghai
    -0.62
    rising
    -0.60
     IOC
    -0.59
     Presidents
    -0.57
     Governors
    -0.57
     Yel
    -0.57
     olds
    -0.57
     inclined
    -0.56
     yourselves
    -0.56
     promulg
    -0.55
    POSITIVE LOGITS
     drawer
    0.95
     stash
    0.95
     wallet
    0.90
     bracelet
    0.89
     password
    0.89
     belongings
    0.88
    mate
    0.86
     jacket
    0.81
     notebook
    0.81
     keys
    0.81
    Activations Density 0.369%

    No Known Activations