© 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. 2-RES-JB
    11. 3913
    Prev
    Next
    INDEX
    Explanations

    references to employers or employment-related terms in text

    oai_token-act-pair · gpt-3.5-turbo

    references to employers or employment-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sheer
    -0.72
    yss
    -0.72
     Revival
    -0.68
     Grip
    -0.66
     BST
    -0.64
    range
    -0.63
    Push
    -0.62
    warm
    -0.61
    math
    -0.60
    pac
    -0.60
    POSITIVE LOGITS
     employer
    1.05
     Employ
    1.01
    employ
    1.01
     employers
    1.00
     employment
    0.80
    chwitz
    0.79
    Employ
    0.79
     Advantage
    0.77
     unions
    0.77
     employee
    0.74
    Activations Density 0.011%

    No Known Activations