© 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. 11-RES-JB
    11. 11623
    Prev
    Next
    INDEX
    Explanations

    actions related to distributing or handing out items

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to distributing items or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    itect
    -0.89
    anship
    -0.83
    Profile
    -0.83
    depth
    -0.81
    Brexit
    -0.78
    ibia
    -0.77
     Dhabi
    -0.76
    Depth
    -0.75
    º
    -0.74
    eda
    -0.74
    POSITIVE LOGITS
     coupons
    1.60
     snacks
    1.41
     candy
    1.37
     packets
    1.36
     flyers
    1.35
     vouchers
    1.35
     sweets
    1.35
     goodies
    1.33
     bottles
    1.31
     treats
    1.31
    Activations Density 0.390%

    No Known Activations