© 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. 11-RES-JB
    11. 17422
    Prev
    Next
    INDEX
    Explanations

    locations, geographical coordinates, and possibly sports team-related information

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to sports statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -1.04
    soDeliveryDate
    -0.89
    isphere
    -0.87
    catentry
    -0.86
     proble
    -0.83
     carbohyd
    -0.80
     explan
    -0.79
    ¥ŀ
    -0.74
     encount
    -0.74
     momentarily
    -0.73
    POSITIVE LOGITS
     0
    1.17
     38
    1.08
     82
    1.05
     42
    1.05
     58
    1.04
     84
    1.04
     78
    1.04
     47
    1.04
     46
    1.04
     88
    1.04
    Activations Density 0.077%

    No Known Activations