© 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. 4-RES-JB
    11. 10166
    Prev
    Next
    INDEX
    Explanations

    references to labor unions or activities related to unions

    oai_token-act-pair · gpt-3.5-turbo

    references to unions and union-related concepts

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

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.77
    hower
    -0.76
    cold
    -0.72
    olitics
    -0.72
     Flavoring
    -0.71
    erva
    -0.69
    »Ĵ
    -0.65
    onso
    -0.65
    articles
    -0.65
    thora
    -0.64
    POSITIVE LOGITS
     federation
    1.07
     unions
    1.07
     union
    1.00
     feder
    1.00
     membership
    0.95
     dues
    0.84
     anthem
    0.81
     organizer
    0.79
    union
    0.79
     Confederation
    0.78
    Activations Density 0.024%

    No Known Activations