© 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
    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. 20421
    Prev
    Next
    INDEX
    Explanations

    information related to employment, work hours, labor laws, and job conditions

    oai_token-act-pair · gpt-3.5-turbo

    information related to employment and labor statistics

    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
    mire
    -0.91
     mosqu
    -0.79
     Ballistic
    -0.78
    canon
    -0.74
     Vaj
    -0.73
    FactoryReloaded
    -0.72
     Juda
    -0.71
     Conspiracy
    -0.71
     Glac
    -0.71
     Cart
    -0.71
    POSITIVE LOGITS
     employers
    1.82
     workers
    1.80
     employment
    1.80
     wage
    1.79
     jobs
    1.79
     wages
    1.77
     employer
    1.75
    Job
    1.75
     workforce
    1.74
    Employ
    1.73
    Activations Density 1.188%

    No Known Activations