Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 24021
    Prev
    Next
    INDEX
    Explanations

    words related to virtual assistants, specifically focusing on Alexa

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Alexa voice assistant and its related functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eways
    -0.75
    ":"/
    -0.71
    udeb
    -0.71
     Sabbath
    -0.68
     WARN
    -0.67
    raft
    -0.67
    neys
    -0.66
    pite
    -0.66
    POS
    -0.65
    emate
    -0.63
    POSITIVE LOGITS
     Alexa
    1.25
     Cortana
    1.02
     lapt
    1.00
     Siri
    0.95
     Bots
    0.85
    ipop
    0.84
    oice
    0.80
    Voice
    0.78
    DonaldTrump
    0.70
    atson
    0.69
    Activations Density 0.007%

    No Known Activations