© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5340
    Prev
    Next
    INDEX
    Explanations

    references to physical bags

    oai_token-act-pair · gpt-3.5-turbo

    references to bags in various contexts

    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
    xxx
    -0.75
     âĨij
    -0.69
    govern
    -0.68
     Livingston
    -0.68
    licts
    -0.68
    auri
    -0.68
    Mars
    -0.67
    FE
    -0.67
    Tenn
    -0.67
    LY
    -0.66
    POSITIVE LOGITS
     bag
    3.66
     bags
    2.69
     Bag
    2.36
    bag
    2.30
    bags
    1.73
     backpack
    1.63
     pouch
    1.61
     suitcase
    1.57
     sack
    1.49
     luggage
    1.46
    Activations Density 0.014%

    No Known Activations