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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8927
    Prev
    Next
    INDEX
    Explanations

    technology-related products and terms, specifically related to Apple and Amazon devices

    oai_token-act-pair · gpt-3.5-turbo

    references to specific electronic devices, particularly Apple products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ©
    -0.83
    steen
    -0.83
     Petr
    -0.79
    orkshire
    -0.73
    redited
    -0.72
    ilitary
    -0.70
    #$#$
    -0.69
     psi
    -0.68
    herty
    -0.68
    nat
    -0.67
    POSITIVE LOGITS
     smartphones
    0.95
     MacBook
    0.94
    Accessory
    0.91
     tablet
    0.89
     OLED
    0.88
     accessories
    0.87
     laptops
    0.87
     ASUS
    0.85
     Samsung
    0.85
     Accessories
    0.84
    Activations Density 0.127%

    No Known Activations