© 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. 10-RES-JB
    11. 11362
    Prev
    Next
    INDEX
    Explanations

    mentions of products or items hitting the market

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating market introduction or launch of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.79
    TION
    -0.73
    isson
    -0.72
     beforehand
    -0.72
     comprised
    -0.72
    milo
    -0.70
    ItemImage
    -0.67
    acca
    -0.66
    wcsstore
    -0.64
     resorted
    -0.64
    POSITIVE LOGITS
     forefront
    1.21
     shelves
    1.16
     shores
    1.15
     masses
    1.10
     mainstream
    1.06
     streets
    1.04
     marketplace
    1.04
     market
    0.98
     continent
    0.96
     skies
    0.95
    Activations Density 0.182%

    No Known Activations