© 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. 18501
    Prev
    Next
    INDEX
    Explanations

    expressions related to quantity like "much" or "many"

    oai_token-act-pair · gpt-3.5-turbo

    the word "much" in various contexts

    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
     Tags
    -0.79
    agate
    -0.68
    ells
    -0.68
    emy
    -0.67
    yss
    -0.66
    abad
    -0.65
    ruby
    -0.65
    hens
    -0.65
    ventures
    -0.64
    İĭ
    -0.63
    POSITIVE LOGITS
     ado
    1.22
     larger
    0.91
     smaller
    0.90
     greater
    0.90
     stricter
    0.87
     shorter
    0.85
     bigger
    0.85
     simpler
    0.85
     heavier
    0.84
     cheaper
    0.83
    Activations Density 0.069%

    No Known Activations