© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18589
    Prev
    Next
    INDEX
    Explanations

    locations of employment and job descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to work or employment in various industries

    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
    Particip
    -0.68
    xual
    -0.67
    orious
    -0.66
    userc
    -0.66
     adherents
    -0.66
    member
    -0.66
     Included
    -0.66
    äºĶ
    -0.65
    Magikarp
    -0.65
    Winged
    -0.65
    POSITIVE LOGITS
     factories
    1.02
     warehouses
    0.99
     landsc
    0.99
     kitchens
    0.98
     subcontract
    0.97
     construction
    0.96
     staffing
    0.96
     catering
    0.96
     outsourcing
    0.94
     consultancy
    0.94
    Activations Density 0.199%

    No Known Activations