© 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. 10-RES-JB
    11. 6583
    Prev
    Next
    INDEX
    Explanations

    comparisons of quantities

    oai_token-act-pair · gpt-3.5-turbo

    phrases or contexts emphasizing quantities or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xtap
    -0.80
    ħĭ
    -0.79
    essage
    -0.77
    ĺħ
    -0.74
    ¬¼
    -0.71
    ı
    -0.70
    vised
    -0.69
    atan
    -0.69
    ij士
    -0.66
    »Ĵ
    -0.65
    POSITIVE LOGITS
     than
    1.92
    than
    1.42
     Than
    1.40
     ado
    0.84
     mouths
    0.78
     bang
    0.76
     importantly
    0.72
    Th
    0.70
     mileage
    0.69
     TH
    0.68
    Activations Density 0.126%

    No Known Activations