© 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. 5124
    Prev
    Next
    INDEX
    Explanations

    specific acronyms related to technology or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to "GS" (presumably a specific term or acronym) related to various topics or themes

    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
     Violet
    -0.72
     pudding
    -0.72
     fil
    -0.68
     violet
    -0.65
     puppet
    -0.64
     Bever
    -0.63
     reaction
    -0.62
     Vienna
    -0.61
     raven
    -0.61
     imm
    -0.61
    POSITIVE LOGITS
    GS
    4.50
    gs
    1.75
     GS
    1.75
    GM
    1.57
    GE
    1.45
    GC
    1.44
    GV
    1.43
    GA
    1.39
    GP
    1.39
    DS
    1.39
    Activations Density 0.010%

    No Known Activations