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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4709
    Prev
    Next
    INDEX
    Explanations

    nouns related to technology and wireless communication

    oai_token-act-pair · gpt-3.5-turbo

    references to wireless technology and networks

    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
    itia
    -0.74
     Scand
    -0.73
    udo
    -0.73
    ablishment
    -0.72
     Yard
    -0.72
    anza
    -0.71
     Hitler
    -0.70
     Bane
    -0.69
     Minerva
    -0.68
     Martinez
    -0.67
    POSITIVE LOGITS
     wireless
    1.13
     broadband
    0.95
     Wireless
    0.90
     networking
    0.90
     connectivity
    0.89
     insulation
    0.88
     coil
    0.88
     imaging
    0.87
     headphones
    0.87
     handset
    0.84
    Activations Density 0.005%

    No Known Activations