© 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. 11-RES-JB
    11. 16535
    Prev
    Next
    INDEX
    Explanations

    mentions of job-related terms, such as job creation, lost jobs, and the number of jobs supported or threatened

    oai_token-act-pair · gpt-3.5-turbo

    references to employment and job statistics

    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
     Tant
    -0.70
    sonian
    -0.69
    mber
    -0.68
    gger
    -0.67
     Wem
    -0.67
     Totem
    -0.66
    quet
    -0.66
     Mast
    -0.64
    thia
    -0.64
    yx
    -0.64
    POSITIVE LOGITS
     jobs
    0.85
     openings
    0.84
     opportunities
    0.83
     displaced
    0.82
     layoffs
    0.81
     outsourcing
    0.81
    killed
    0.79
    anooga
    0.76
     postings
    0.75
     shortages
    0.74
    Activations Density 0.080%

    No Known Activations