© 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. 2-RES-JB
    11. 12516
    Prev
    Next
    INDEX
    Explanations

    numerical quantities related to the amount or volume of things, especially when expressed as units or items

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities of items or units sold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.70
     Opportun
    -0.69
    æĢ
    -0.69
     Shack
    -0.67
    é»Ĵ
    -0.67
     vengeance
    -0.63
    ãĤ¨ãĥ«
    -0.63
    ãĤī
    -0.62
     havoc
    -0.62
    uez
    -0.62
    POSITIVE LOGITS
     units
    1.03
    units
    0.96
    imet
    0.94
    matically
    0.89
    mates
    0.88
    etting
    0.86
    arily
    0.85
    mate
    0.84
    rity
    0.82
     unit
    0.80
    Activations Density 0.010%

    No Known Activations