© 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. 8-RES-JB
    11. 6933
    Prev
    Next
    INDEX
    Explanations

    locations or establishments related to shopping

    oai_token-act-pair · gpt-3.5-turbo

    references to shops or retail establishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioxide
    -0.67
     Species
    -0.65
     dreaded
    -0.63
     Marketable
    -0.62
     IPCC
    -0.61
    emonic
    -0.61
     Highlands
    -0.59
     POW
    -0.58
     precipitation
    -0.58
     Persons
    -0.58
    POSITIVE LOGITS
    keepers
    1.38
    keeper
    1.38
    lifting
    1.23
    worn
    1.09
    shop
    1.08
    kie
    1.02
    front
    0.93
    keep
    0.93
    folk
    0.91
    ify
    0.91
    Activations Density 0.028%

    No Known Activations