© 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. 11-RES-JB
    11. 2598
    Prev
    Next
    INDEX
    Explanations

    references to financial matters related to low-income individuals and government assistance programs

    oai_token-act-pair · gpt-3.5-turbo

    references to low-income individuals and their financial challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Newsp
    -0.69
     Canaver
    -0.69
     Mahjong
    -0.68
    choes
    -0.64
     Guinness
    -0.63
     Cerberus
    -0.63
     Pengu
    -0.62
    cot
    -0.62
     Glac
    -0.62
    natureconservancy
    -0.61
    POSITIVE LOGITS
    income
    1.50
     income
    1.23
     earners
    1.20
     incomes
    1.06
    skilled
    1.06
    wealth
    1.03
    wage
    1.01
    paid
    1.01
     achie
    1.01
     socioeconomic
    0.95
    Activations Density 0.093%

    No Known Activations