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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12731
    Prev
    Next
    INDEX
    Explanations

    terms related to virtual assistants like Siri and Alexa

    oai_token-act-pair · gpt-3.5-turbo

    references to voice activated digital assistants

    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
     Krugman
    -0.83
    nian
    -0.82
    rar
    -0.77
    anches
    -0.75
    abama
    -0.74
    emetery
    -0.71
    pite
    -0.70
     Sabb
    -0.70
    imbabwe
    -0.69
    udeb
    -0.69
    POSITIVE LOGITS
     wearable
    1.25
     headsets
    1.23
     headset
    1.19
     devices
    1.18
     sensors
    1.18
     wireless
    1.11
     Bluetooth
    1.11
     sensor
    1.10
     Siri
    1.10
     gadgets
    1.07
    Activations Density 0.131%

    No Known Activations