© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 7033
    Prev
    Next
    INDEX
    Explanations

    terms related to physical structures, especially roofs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of roofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.86
     MacArthur
    -0.79
    avez
    -0.78
    inational
    -0.72
     Schumer
    -0.72
    emonic
    -0.69
    nesia
    -0.68
     ALS
    -0.67
    ppe
    -0.65
     Holden
    -0.65
    POSITIVE LOGITS
     roof
    0.97
    deck
    0.94
     terr
    0.93
     ornament
    0.90
     tops
    0.89
     rack
    0.89
    ed
    0.83
    buster
    0.81
     canopy
    0.81
     racks
    0.80
    Activations Density 0.032%

    No Known Activations