© 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. 2-RES-JB
    11. 21208
    Prev
    Next
    INDEX
    Explanations

    mentions of real estate properties, specifically condos

    oai_token-act-pair · gpt-3.5-turbo

    references to condos and apartment units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ²¾
    -0.73
    saf
    -0.72
    Published
    -0.70
    nesses
    -0.69
    akia
    -0.67
    ym
    -0.67
    ker
    -0.67
    kers
    -0.65
    mic
    -0.64
    uncture
    -0.64
    POSITIVE LOGITS
     condos
    1.34
     condo
    1.23
     apartments
    1.17
    ominium
    1.03
     rentals
    0.97
     apartment
    0.95
     occupancy
    0.93
     towers
    0.85
    creen
    0.81
     housing
    0.80
    Activations Density 0.012%

    No Known Activations