© 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. 11-RES-JB
    11. 20348
    Prev
    Next
    INDEX
    Explanations

    real estate-related terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to real estate

    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
     Daylight
    -0.79
    olics
    -0.78
    warts
    -0.76
    thia
    -0.72
     Kali
    -0.72
    nah
    -0.71
    osi
    -0.68
    gans
    -0.67
    renheit
    -0.67
    toe
    -0.67
    POSITIVE LOGITS
     brokerage
    1.27
     brokers
    1.25
     broker
    1.22
     mogul
    1.22
     agent
    1.15
     listings
    1.12
     agents
    1.09
     mog
    1.08
     holdings
    1.06
     prices
    1.06
    Activations Density 0.072%

    No Known Activations