© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 21001
    Prev
    Next
    INDEX
    Explanations

    terms related to gentrification and gentrifying neighborhoods

    oai_token-act-pair · gpt-3.5-turbo

    references to neighborhoods undergoing gentrification

    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
    aeda
    -0.94
    ĸļ
    -0.94
    igslist
    -0.79
    nesota
    -0.77
     Pradesh
    -0.75
    Accessory
    -0.75
    braska
    -0.73
    ibaba
    -0.72
    Downloadha
    -0.70
    ptin
    -0.70
    POSITIVE LOGITS
    rification
    1.16
    rified
    1.03
    ility
    1.00
    gart
    0.99
    iour
    0.98
     Gent
    0.94
    leness
    0.89
    lest
    0.89
    ified
    0.88
     gent
    0.88
    Activations Density 0.005%

    No Known Activations