© 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. 10-RES-JB
    11. 18699
    Prev
    Next
    INDEX
    Explanations

    GT class wins and updates or versions in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    elements related to measurements and statistics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¶
    -0.94
    OST
    -0.92
    Ó
    -0.89
    Lua
    -0.88
    Ãĥ
    -0.88
     Beef
    -0.88
    Products
    -0.87
    Ro
    -0.87
    Especially
    -0.87
    ¯
    -0.86
    POSITIVE LOGITS
     nod
    0.96
     hover
    0.94
     goodbye
    0.93
     rethink
    0.90
     arrange
    0.90
     mont
    0.89
     farewell
    0.87
     dream
    0.87
     sue
    0.86
     ponder
    0.86
    Activations Density 0.469%

    No Known Activations