© 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. 1-RES-JB
    11. 22697
    Prev
    Next
    INDEX
    Explanations

    mentions of specific company names, particularly Microsoft

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Microsoft brand

    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
     toget
    -0.86
    ãĤ¨ãĥ«
    -0.79
    undred
    -0.71
    mercial
    -0.68
     Gerard
    -0.66
    appiness
    -0.65
    Population
    -0.65
    姫
    -0.64
     circulate
    -0.64
     modern
    -0.62
    POSITIVE LOGITS
    videos
    0.86
    croft
    0.66
    hall
    0.63
    âĢ²
    0.62
    hover
    0.61
     Tus
    0.61
    bilt
    0.60
     Wire
    0.60
     Chiefs
    0.60
    pine
    0.60
    Activations Density 0.000%

    No Known Activations