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. 4-RES-JB
    6. 23093
    Prev
    Next
    INDEX
    Explanations

    references to different aspects of the concept of rent, including payment, costs, and financial impact

    oai_token-act-pair · gpt-3.5-turbo

    references to rent and related financial concepts

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

    No Comments

    Negative Logits
    doi
    -0.83
     Flavoring
    -0.81
    ctions
    -0.72
    ometown
    -0.71
    IJ
    -0.68
    aque
    -0.67
     Chemistry
    -0.67
    olics
    -0.65
    lde
    -0.65
    ================================================================
    -0.64
    POSITIVE LOGITS
     rent
    0.94
     renting
    0.86
     renters
    0.84
     Rent
    0.82
     rented
    0.80
     apartments
    0.80
     rents
    0.77
    Chart
    0.76
     cheaply
    0.75
     Estate
    0.73
    Activations Density 0.009%

    No Known Activations