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. 9-RES-JB
    6. 22457
    Prev
    Next
    INDEX
    Explanations

    phrases related to income levels and socio-economic status

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to socio-economic disparities and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dl
    -0.71
    ynthesis
    -0.61
    \\\\\\\\
    -0.60
    esh
    -0.59
    inness
    -0.58
     muse
    -0.57
    planet
    -0.57
    agram
    -0.57
     compass
    -0.57
    arta
    -0.56
    POSITIVE LOGITS
    those
    1.17
     ones
    1.04
     those
    0.97
     elderly
    0.96
     areas
    0.95
     affluent
    0.91
     wealthier
    0.87
     disadvantaged
    0.87
     outl
    0.85
     seniors
    0.84
    Activations Density 1.025%

    No Known Activations