© 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. 20887
    Prev
    Next
    INDEX
    Explanations

    keywords related to constructions or building activities

    oai_token-act-pair · gpt-3.5-turbo

    references to construction activities and processes

    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
    Gene
    -0.75
    romeda
    -0.75
    andra
    -0.75
    leon
    -0.73
    flix
    -0.68
    olate
    -0.67
    BILITIES
    -0.67
    rition
    -0.66
    Cola
    -0.64
    bern
    -0.63
    POSITIVE LOGITS
     crews
    1.01
     materials
    0.94
     crane
    0.92
     permits
    0.91
     worker
    0.89
     projects
    0.87
     boom
    0.86
     scaff
    0.86
     permit
    0.85
     workers
    0.84
    Activations Density 0.058%

    No Known Activations