© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3277
    Prev
    Next
    INDEX
    Explanations

    phrases related to serving or being of service, especially to a community or country

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to service to the community and country

    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
    SpaceEngineers
    -0.63
     Collider
    -0.61
    ihar
    -0.61
     Tracking
    -0.57
    Cs
    -0.56
     manoeuv
    -0.56
    NC
    -0.56
    fusc
    -0.55
    Completed
    -0.54
    Applic
    -0.54
    POSITIVE LOGITS
     faithfully
    1.09
    selves
    0.96
     sake
    0.90
     uncond
    0.89
     dearly
    0.87
     sacrific
    0.87
     properly
    0.84
     wisely
    0.82
     safely
    0.81
     efficiently
    0.79
    Activations Density 0.268%

    No Known Activations