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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 3368
    Prev
    Next
    INDEX
    Explanations

    words related to social class and working-class themes

    oai_token-act-pair · gpt-3.5-turbo

    references to the working class

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Manson
    -0.70
     flares
    -0.66
     toast
    -0.65
    etsk
    -0.65
     vaccinations
    -0.64
     hail
    -0.62
     Faw
    -0.62
    eters
    -0.62
     concise
    -0.61
     vaccines
    -0.61
    POSITIVE LOGITS
    class
    1.12
    rate
    1.06
    skill
    1.06
    life
    1.05
    related
    1.03
    wage
    1.02
    home
    1.00
    contract
    1.00
    disabled
    0.99
    union
    0.98
    Activations Density 0.060%

    No Known Activations