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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12604
    Prev
    Next
    INDEX
    Explanations

    references to social classes, especially the middle class

    oai_token-act-pair · gpt-3.5-turbo

    references to the middle class

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TAG
    -0.79
    Downloadha
    -0.77
    inventoryQuantity
    -0.74
     Archdemon
    -0.74
     Mast
    -0.67
    SCP
    -0.67
    oldown
    -0.67
    soDeliveryDate
    -0.66
    KEY
    -0.65
    sbm
    -0.64
    POSITIVE LOGITS
     earners
    0.93
     incomes
    0.82
    ifications
    0.73
    naire
    0.71
    ocrats
    0.70
     Revival
    0.69
     mobility
    0.68
     retirees
    0.68
     taxp
    0.68
     families
    0.67
    Activations Density 0.018%

    No Known Activations