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. 7-RES-JB
    6. 4573
    Prev
    Next
    INDEX
    Explanations

    references to income and income distribution

    oai_token-act-pair · gpt-3.5-turbo

    references to income and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toe
    -0.77
    OY
    -0.74
    soDeliveryDate
    -0.70
    ategory
    -0.70
    abies
    -0.69
    lain
    -0.69
    eries
    -0.69
    aptic
    -0.69
    士
    -0.67
    ery
    -0.66
    POSITIVE LOGITS
     earners
    1.30
     income
    1.03
     taxes
    1.02
     inequality
    1.01
     Income
    0.96
     tax
    0.96
     Taxes
    0.94
     streams
    0.92
     disparity
    0.89
     redistribution
    0.87
    Activations Density 0.030%

    No Known Activations