© 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. 6232
    Prev
    Next
    INDEX
    Explanations

    business activities or projects related to construction and development

    oai_token-act-pair · gpt-3.5-turbo

    projects related to construction and development of public facilities

    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
     bruises
    -0.64
     Tsukuyomi
    -0.63
    inventoryQuantity
    -0.62
    istered
    -0.62
    Reward
    -0.61
    licks
    -0.61
    metics
    -0.61
    RESULTS
    -0.61
    maxwell
    -0.59
     phrases
    -0.58
    POSITIVE LOGITS
     overlooking
    1.02
     adjacent
    0.98
     atop
    0.97
     located
    0.96
     inside
    0.96
     nearby
    0.95
     modeled
    0.93
     near
    0.93
     downtown
    0.93
     situated
    0.91
    Activations Density 0.280%

    No Known Activations