© 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. 10-RES-JB
    11. 15979
    Prev
    Next
    INDEX
    Explanations

    phrases indicating willingness to assist or provide information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    requests for specific actions to be taken or information to be provided

    oai_token-act-pair · gpt-3.5-turbo
    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
    NAS
    -0.76
    inventoryQuantity
    -0.71
    quickShipAvailable
    -0.69
    utical
    -0.69
    netflix
    -0.68
    çīĪ
    -0.65
     restraint
    -0.65
    Parents
    -0.63
    erva
    -0.63
    assault
    -0.61
    POSITIVE LOGITS
     gladly
    1.10
     kindly
    0.90
     answ
    0.89
     reply
    0.85
    send
    0.82
     arrange
    0.81
     forwarded
    0.79
     refund
    0.77
     chat
    0.75
     organise
    0.75
    Activations Density 0.217%

    No Known Activations