© 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. 3-RES-JB
    11. 16248
    Prev
    Next
    INDEX
    Explanations

    information related to real estate, specifically focusing on units, affordability, homeownership, and housing properties

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to housing and residential units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bleach
    -0.72
    rawdownloadcloneembedreportprint
    -0.72
     Canaver
    -0.70
     Lethal
    -0.68
    UTH
    -0.67
    ipher
    -0.67
     Paste
    -0.66
    £ı
    -0.65
     consistency
    -0.64
     flesh
    -0.63
    POSITIVE LOGITS
     mortgages
    1.19
     apartments
    1.18
     rentals
    1.14
     condos
    1.14
     rental
    1.12
     dwellings
    1.09
     housing
    0.99
     mortgage
    0.98
    ominium
    0.98
     Mortgage
    0.97
    Activations Density 0.177%

    No Known Activations