© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 8289
    Prev
    Next
    INDEX
    Explanations

    mentions of the company "Microsoft" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the company Microsoft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    outh
    -0.76
    vae
    -0.74
    bath
    -0.71
    Tar
    -0.69
     Purg
    -0.68
    anc
    -0.68
     plate
    -0.68
    ruck
    -0.68
     isot
    -0.67
     Tar
    -0.66
    POSITIVE LOGITS
     Microsoft
    3.39
    Microsoft
    3.14
    microsoft
    2.29
     Nokia
    1.92
     Mozilla
    1.85
     Windows
    1.83
     IBM
    1.80
     Redmond
    1.79
     Adobe
    1.73
     Lenovo
    1.72
    Activations Density 0.017%

    No Known Activations