© 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. 18884
    Prev
    Next
    INDEX
    Explanations

    references to consumer-related terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to consumers and consumer-related topics

    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
    spell
    -0.62
    numbered
    -0.61
    lap
    -0.60
     chapel
    -0.60
     Chance
    -0.60
     Shard
    -0.59
     Ward
    -0.59
    ship
    -0.58
     Pos
    -0.58
    zik
    -0.58
    POSITIVE LOGITS
     consumers
    3.48
     Consumers
    2.62
    umers
    2.39
     consumer
    2.24
    consumer
    2.22
     shoppers
    2.18
     customers
    2.12
    Consumer
    2.05
     buyers
    1.97
     marketers
    1.90
    Activations Density 0.018%

    No Known Activations