© 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. 8-RES-JB
    11. 23726
    Prev
    Next
    INDEX
    Explanations

    the phrase "one or two"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify or reference small numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lance
    -0.89
    andise
    -0.73
    NAS
    -0.73
    nect
    -0.69
    STAT
    -0.69
    gow
    -0.69
    adder
    -0.67
    nor
    -0.67
    ater
    -0.65
    andr
    -0.65
    POSITIVE LOGITS
     dozen
    1.12
     hundred
    1.08
     thousand
    1.02
     exceptions
    0.95
     batches
    0.87
     thirds
    0.86
     times
    0.80
     occasions
    0.79
     generations
    0.78
     editions
    0.78
    Activations Density 0.047%

    No Known Activations