© 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. 11239
    Prev
    Next
    INDEX
    Explanations

    phrases related to products or entities being removed or disappearing from a market or shelves

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to products entering or leaving the market

    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
    wcsstore
    -0.76
    MpServer
    -0.75
    ascript
    -0.74
    maid
    -0.74
    VIDIA
    -0.72
    SourceFile
    -0.71
    osta
    -0.70
    anka
    -0.68
    ga
    -0.66
    arse
    -0.65
    POSITIVE LOGITS
     shelves
    1.20
     circulation
    1.19
     classrooms
    1.04
     theaters
    1.03
     obscurity
    0.97
     mainstream
    0.96
     shores
    0.94
     supermarkets
    0.89
     stores
    0.87
     fruition
    0.86
    Activations Density 0.276%

    No Known Activations