Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10431
    Prev
    Next
    INDEX
    Explanations

    references to the company Airbnb

    oai_token-act-pair · gpt-3.5-turbo

    references to Airbnb and its impact on various aspects of the housing market

    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
    aneous
    -0.80
    inas
    -0.80
    aneously
    -0.78
    rez
    -0.77
    ional
    -0.77
    ION
    -0.76
    utical
    -0.71
    seys
    -0.70
    ocr
    -0.69
    usalem
    -0.69
    POSITIVE LOGITS
    bnb
    1.35
     Airbnb
    0.99
     rentals
    0.80
     eviction
    0.69
     renters
    0.69
    Host
    0.68
    trop
    0.68
     evict
    0.67
     tenants
    0.67
     occupancy
    0.67
    Activations Density 0.014%

    No Known Activations