© 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. 9-RES-JB
    11. 9996
    Prev
    Next
    INDEX
    Explanations

    references to delivery or delivering items or services

    oai_token-act-pair · gpt-3.5-turbo

    terms related to delivery services and logistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maxwell
    -0.77
    ounty
    -0.77
    owler
    -0.72
    anu
    -0.72
    sem
    -0.71
    acebook
    -0.68
    utory
    -0.68
     Mori
    -0.68
    kered
    -0.67
    wikipedia
    -0.67
    POSITIVE LOGITS
     deliveries
    1.12
     delivery
    1.02
    Delivery
    0.94
     trucks
    0.86
     delivered
    0.85
     Delivery
    0.84
     truck
    0.83
     service
    0.79
     courier
    0.78
    loads
    0.77
    Activations Density 0.051%

    No Known Activations