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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 9963
    Prev
    Next
    INDEX
    Explanations

    mentions of physical structures relating to roofs

    oai_token-act-pair · gpt-3.5-turbo

    references to roofs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.90
    nesia
    -0.76
    avez
    -0.74
    ADRA
    -0.71
     MacArthur
    -0.68
     Schumer
    -0.68
     ALS
    -0.67
     Sacrament
    -0.67
     CNS
    -0.64
    ocus
    -0.64
    POSITIVE LOGITS
     terr
    1.05
     roof
    1.05
    deck
    0.97
     roofs
    0.92
     tops
    0.92
     canopy
    0.91
     tiles
    0.91
     rack
    0.91
    line
    0.90
     racks
    0.86
    Activations Density 0.031%

    No Known Activations