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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3154
    Prev
    Next
    INDEX
    Explanations

    phrases related to social classes and economic status

    oai_token-act-pair · gpt-3.5-turbo

    references to the working and middle class, particularly in a political or economic context

    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
    inventoryQuantity
    -0.84
    uberty
    -0.79
    SIGN
    -0.77
    oldown
    -0.76
    Recomm
    -0.75
    ciating
    -0.75
     Protocol
    -0.74
    bsp
    -0.73
    opy
    -0.72
    sites
    -0.72
    POSITIVE LOGITS
     earners
    1.10
     families
    1.00
     incomes
    0.99
     whites
    0.96
     households
    0.96
     peasants
    0.95
     bourgeoisie
    0.90
     peasant
    0.89
     wages
    0.88
     estates
    0.88
    Activations Density 0.061%

    No Known Activations