© 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. 11-RES-JB
    11. 9523
    Prev
    Next
    INDEX
    Explanations

    percentages and proportions of different groups or quantities in a text

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations of data and statistics related to demographics or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.73
    代
    -0.68
    Synopsis
    -0.67
    inventoryQuantity
    -0.66
    ¥µ
    -0.64
    é»Ĵ
    -0.59
    quished
    -0.59
    ĸļ
    -0.58
    adobe
    -0.58
    itialized
    -0.58
    POSITIVE LOGITS
     85
    1.24
     80
    1.24
     majorities
    1.22
     95
    1.22
     98
    1.21
     92
    1.20
     majority
    1.20
     75
    1.19
     97
    1.19
     93
    1.19
    Activations Density 0.584%

    No Known Activations