© 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. 4-RES-JB
    11. 17084
    Prev
    Next
    INDEX
    Explanations

    words related to desire or craving

    oai_token-act-pair · gpt-3.5-turbo

    references to appetite or desire, particularly in various contexts

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

    No Comments

    Negative Logits
    mberg
    -0.81
    gaard
    -0.74
     Gentle
    -0.73
     Offic
    -0.71
     Obst
    -0.70
    ogie
    -0.70
     Mehran
    -0.69
     Roses
    -0.68
    stood
    -0.68
     Conduct
    -0.66
    POSITIVE LOGITS
     appetite
    1.41
     appet
    0.92
     eater
    0.83
     hunger
    0.81
     craving
    0.81
     hungry
    0.77
     thirst
    0.75
    ibal
    0.74
    ocity
    0.74
    igue
    0.73
    Activations Density 0.013%

    No Known Activations