© 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. 22508
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Consumer" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of consumer-related topics or organizations

    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
     fug
    -0.76
     king
    -0.73
     kings
    -0.71
     artillery
    -0.70
     nig
    -0.68
     align
    -0.68
     sword
    -0.67
     hex
    -0.67
     transl
    -0.66
    fuck
    -0.66
    POSITIVE LOGITS
     Consumer
    3.86
    Consumer
    2.78
     Consumers
    2.13
    consumer
    1.83
     consumer
    1.63
     Customer
    1.34
     Environmental
    1.34
     Retail
    1.34
     CES
    1.31
     Investor
    1.27
    Activations Density 0.009%

    No Known Activations