© 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. 0-RES-JB
    11. 19039
    Prev
    Next
    INDEX
    Explanations

    mentions of specific 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
    -0.75
    frog
    -0.69
     Pres
    -0.68
    onso
    -0.65
     Bates
    -0.64
     Recomm
    -0.63
    ::::::::
    -0.62
    Haunted
    -0.61
    croft
    -0.61
    ooks
    -0.61
    POSITIVE LOGITS
     union
    4.02
     unions
    3.04
    union
    2.60
    Union
    2.44
     Union
    2.24
     federation
    1.55
     association
    1.34
     unification
    1.18
     labor
    1.18
     bargaining
    1.09
    Activations Density 0.019%

    No Known Activations