© 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. 7-RES-JB
    11. 1650
    Prev
    Next
    INDEX
    Explanations

    opportunities for involvement or participation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating opportunities or chances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.78
    requires
    -0.77
     Needs
    -0.71
    wise
    -0.70
    advertising
    -0.70
     Falls
    -0.68
     Direction
    -0.66
    quickShipAvailable
    -0.66
     Mysterious
    -0.66
    Wire
    -0.64
    POSITIVE LOGITS
     explore
    1.20
     indulge
    1.19
     learn
    1.15
     participate
    1.15
     educate
    1.11
     capitalize
    1.11
     engage
    1.10
     fulfill
    1.07
     demonstrate
    1.06
     showcase
    1.04
    Activations Density 0.089%

    No Known Activations