© 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. 11-RES-JB
    11. 14953
    Prev
    Next
    INDEX
    Explanations

    phrases related to creating or forming something

    oai_token-act-pair · gpt-3.5-turbo

    elements related to the act of creating or building something

    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
    inventoryQuantity
    -0.94
    terness
    -0.88
    isSpecialOrderable
    -0.78
    autions
    -0.75
    ources
    -0.73
    techn
    -0.72
    Magikarp
    -0.70
    oft
    -0.69
    uracy
    -0.68
    SPONSORED
    -0.68
    POSITIVE LOGITS
     masterpiece
    1.14
     replica
    1.04
     customized
    1.04
     cohesive
    1.03
     makeshift
    1.02
     playlist
    1.02
     personalized
    1.02
     profile
    0.99
     custom
    0.97
     composite
    0.97
    Activations Density 0.203%

    No Known Activations