© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 21514
    Prev
    Next
    INDEX
    Explanations

    words related to sweetness or sweet substances

    oai_token-act-pair · gpt-3.5-turbo

    references to sugary substances and sweeteners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WARN
    -0.77
     Mub
    -0.73
     Rent
    -0.73
     DRAG
    -0.72
     FAA
    -0.72
     RIS
    -0.71
     Patel
    -0.71
     Sigma
    -0.69
     Rahman
    -0.69
     Rac
    -0.68
    POSITIVE LOGITS
    gary
    1.41
    weet
    0.98
    ened
    0.96
    wagen
    0.92
    sweet
    0.91
    eners
    0.91
    bourne
    0.90
    axy
    0.87
    jriwal
    0.87
    otine
    0.87
    Activations Density 0.016%

    No Known Activations