© 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. 1811
    Prev
    Next
    INDEX
    Explanations

    items or objects within text

    oai_token-act-pair · gpt-3.5-turbo

    references to various items, particularly in a shopping or inventory context

    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
     pronounced
    -0.71
    zai
    -0.70
    sis
    -0.70
    ilee
    -0.70
    nery
    -0.67
    rome
    -0.65
    iversity
    -0.65
    gow
    -0.65
     chorus
    -0.65
    iya
    -0.64
    POSITIVE LOGITS
     items
    3.57
     Items
    2.84
    items
    2.72
     item
    2.67
    Items
    2.42
    item
    1.93
    Item
    1.93
     Item
    1.89
     goods
    1.69
     objects
    1.66
    Activations Density 0.020%

    No Known Activations