© 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. 10381
    Prev
    Next
    INDEX
    Explanations

    phrases starting with 'Doctor' or 'Dr.' along with some surrounding context

    oai_token-act-pair · gpt-3.5-turbo

    structures related to legislative processes and actions

    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
    boro
    -0.72
     orchestr
    -0.69
     purs
    -0.68
     wiser
    -0.67
    hement
    -0.67
     honoured
    -0.63
     Saiyan
    -0.62
     appe
    -0.62
     marching
    -0.62
     undet
    -0.61
    POSITIVE LOGITS
    ³³³³
    1.00
    Newsletter
    1.00
    Advertisement
    0.99
    ³³³³³³³³³³³³³³³³
    0.97
    SPONSORED
    0.91
    ³³³³³³³³
    0.91
    ³³³
    0.88
    Conclusion
    0.88
    Meanwhile
    0.87
    ³³
    0.84
    Activations Density 1.632%

    No Known Activations