© 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. 11-RES-JB
    11. 10235
    Prev
    Next
    INDEX
    Explanations

    mentions of business executives and company updates

    oai_token-act-pair · gpt-3.5-turbo

    references to influential figures in the technology industry, particularly related to Microsoft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Venezuel
    -1.00
    Cruz
    -0.95
     Wichita
    -0.95
     gh
    -0.93
     Maduro
    -0.91
    Tx
    -0.91
     Freddy
    -0.90
     Cruz
    -0.87
     Lancaster
    -0.86
     corrid
    -0.86
    POSITIVE LOGITS
     Microsoft
    2.26
    Microsoft
    2.13
     Redmond
    1.98
     Cortana
    1.94
     Nokia
    1.90
     Lumia
    1.89
     Windows
    1.86
     Xbox
    1.73
    microsoft
    1.73
     Azure
    1.66
    Activations Density 0.286%

    No Known Activations