© 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. 10265
    Prev
    Next
    INDEX
    Explanations

    the word 'hundreds' repeated multiple times

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities or numbers, specifically the word "hundreds."

    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
    lein
    -0.70
    elman
    -0.67
    ibe
    -0.66
     Neutral
    -0.66
    nor
    -0.64
     (+
    -0.64
    ow
    -0.63
     Relative
    -0.63
    ib
    -0.63
    ibl
    -0.62
    POSITIVE LOGITS
     hundreds
    3.14
     thousands
    2.84
     tens
    2.65
     millions
    2.53
     dozens
    2.52
     billions
    2.42
     trillions
    2.20
    undreds
    2.18
     countless
    2.11
     Hundreds
    2.03
    Activations Density 0.009%

    No Known Activations