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. 8-RES-JB
    6. 14796
    Prev
    Next
    INDEX
    Explanations

    phrases related to socioeconomic status, particularly focusing on low-income individuals and families

    oai_token-act-pair · gpt-3.5-turbo

    references to low-income individuals and families

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.92
    natureconservancy
    -0.86
    pload
    -0.82
    orial
    -0.81
    ynthesis
    -0.80
    witch
    -0.77
    SCP
    -0.76
    hunt
    -0.75
    ampoo
    -0.75
    apo
    -0.74
    POSITIVE LOGITS
     earners
    1.52
     households
    1.16
     tract
    0.97
     families
    0.96
     neighborhoods
    0.96
     immigrants
    0.92
     tracts
    0.92
     backgrounds
    0.91
     laborers
    0.90
     countries
    0.90
    Activations Density 0.044%

    No Known Activations