© 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. 8-RES-JB
    11. 15585
    Prev
    Next
    INDEX
    Explanations

    keywords related to Microsoft products, specifically the Surface line

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific Surface Book products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    govtrack
    -0.86
    arial
    -0.81
    anthrop
    -0.79
    Ô
    -0.75
    atory
    -0.73
    severe
    -0.72
    atories
    -0.72
    pmwiki
    -0.72
    uckland
    -0.71
    ricks
    -0.71
    POSITIVE LOGITS
     MacBook
    0.89
     XL
    0.88
     accessories
    0.87
     Wireless
    0.86
     Accessories
    0.86
     Maker
    0.85
     prototypes
    0.85
    Maker
    0.81
     Mobility
    0.80
     lineup
    0.79
    Activations Density 0.124%

    No Known Activations