© 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. 0-RES-JB
    11. 2816
    Prev
    Next
    INDEX
    Explanations

    mentions or references to labor unions

    oai_token-act-pair · gpt-3.5-turbo

    references to labor unions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zel
    -0.87
    ocular
    -0.84
     Proceed
    -0.68
    lain
    -0.65
    bsite
    -0.65
     Pres
    -0.63
    case
    -0.63
    ander
    -0.63
    ffer
    -0.61
    Admin
    -0.60
    POSITIVE LOGITS
     unions
    4.11
     union
    2.73
    Union
    2.00
    union
    1.92
     associations
    1.49
     Union
    1.39
     pensions
    1.34
     employers
    1.29
     workplaces
    1.23
     marriages
    1.19
    Activations Density 0.010%

    No Known Activations