© 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. 0-RES-JB
    11. 10385
    Prev
    Next
    INDEX
    Explanations

    phrases related to serving or providing something to someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "serves" indicating functionality or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     panic
    -0.67
     cyan
    -0.60
    lot
    -0.58
     Cyan
    -0.57
    TPPStreamerBot
    -0.57
     saying
    -0.55
    cale
    -0.55
    IFT
    -0.55
     scept
    -0.54
     caravan
    -0.54
    POSITIVE LOGITS
     serves
    3.32
     served
    2.16
     serve
    2.16
     serving
    1.67
     Serving
    1.60
     represents
    1.57
     Serve
    1.52
     contributes
    1.51
     provides
    1.51
     operates
    1.46
    Activations Density 0.014%

    No Known Activations