© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 5114
    Prev
    Next
    INDEX
    Explanations

    instances of the word "income"

    oai_token-act-pair · gpt-3.5-turbo

    references to income and financial topics

    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
    士
    -0.74
    abies
    -0.71
    pload
    -0.69
    eries
    -0.66
    aptic
    -0.66
    uj
    -0.65
    ovie
    -0.64
    OY
    -0.63
     Bolt
    -0.63
    apple
    -0.63
    POSITIVE LOGITS
     earners
    1.18
     income
    1.03
     inequality
    0.96
     Income
    0.95
     taxes
    0.90
     earnings
    0.87
     tax
    0.86
     streams
    0.85
     disparity
    0.84
     taxation
    0.82
    Activations Density 0.023%

    No Known Activations