© 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
    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. 2671
    Prev
    Next
    INDEX
    Explanations

    phrases related to social classes, particularly the middle class

    oai_token-act-pair · gpt-3.5-turbo

    references to socioeconomic class, particularly middle-class dynamics

    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
     Shutterstock
    -0.74
     Canaver
    -0.73
     Phi
    -0.67
     GIF
    -0.66
     Cortana
    -0.64
     Logo
    -0.61
     simul
    -0.61
     confir
    -0.61
     Incarn
    -0.61
     fireworks
    -0.61
    POSITIVE LOGITS
    class
    1.52
    income
    1.37
    aged
    1.37
    distance
    1.30
    middle
    1.29
    classes
    1.27
    earth
    1.24
    sized
    1.24
    ranking
    1.21
    upper
    1.20
    Activations Density 0.032%

    No Known Activations