© 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. 15981
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a process, especially related to heating, burning, or changing the physical state of a material

    oai_token-act-pair · gpt-3.5-turbo

    words related to cooking or food preparation processes

    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
    ORTS
    -0.69
    istani
    -0.61
    omics
    -0.58
     CTR
    -0.57
     subordinate
    -0.57
     renaissance
    -0.56
    é¾į
    -0.56
     deleg
    -0.56
    ocally
    -0.56
     ranked
    -0.56
    POSITIVE LOGITS
     pores
    0.98
     coating
    0.87
     moisture
    0.86
     underneath
    0.83
     :(
    0.83
     fibers
    0.82
     afterwards
    0.81
     easily
    0.80
     afterward
    0.79
     prematurely
    0.78
    Activations Density 0.232%

    No Known Activations