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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 22885
    Prev
    Next
    INDEX
    Explanations

    words related to socioeconomic status and financial disparity, particularly focusing on poverty and the elderly

    oai_token-act-pair · gpt-3.5-turbo

    references to socioeconomic issues affecting marginalized groups

    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
    Reviewer
    -0.74
     Carbuncle
    -0.74
     VIDEOS
    -0.70
    forcement
    -0.70
    ciation
    -0.68
     Explos
    -0.68
    DAQ
    -0.67
     Mutual
    -0.67
    emonium
    -0.66
     Donation
    -0.66
    POSITIVE LOGITS
     unemployed
    1.42
     disadvantaged
    1.40
     marginalized
    1.36
     disabled
    1.31
     minorities
    1.27
     elderly
    1.27
     disenfranch
    1.26
     oppressed
    1.26
     needy
    1.20
     impoverished
    1.20
    Activations Density 0.154%

    No Known Activations