© 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. 1-RES-JB
    11. 3879
    Prev
    Next
    INDEX
    Explanations

    references to remaining quantities or portions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "remainder" in a context related to distribution or allocation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gio
    -0.68
    vet
    -0.66
    idden
    -0.65
    arms
    -0.64
    rises
    -0.64
    ku
    -0.63
    into
    -0.62
    bara
    -0.62
    cause
    -0.61
    wired
    -0.58
    POSITIVE LOGITS
     remainder
    1.03
    ĸļ
    0.88
     4090
    0.87
     thereof
    0.86
     newcom
    0.81
    recated
    0.80
    sburg
    0.79
    ructure
    0.77
    swer
    0.77
    EMBER
    0.75
    Activations Density 0.002%

    No Known Activations