Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 22302
    Prev
    Next
    INDEX
    Explanations

    keywords related to appetite

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "appetite" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mberg
    -0.78
    gaard
    -0.73
    oning
    -0.72
    ogie
    -0.68
     Offic
    -0.68
    chester
    -0.67
     Universities
    -0.67
     Gentle
    -0.66
     Obst
    -0.65
     Petra
    -0.65
    POSITIVE LOGITS
     appetite
    1.41
     appet
    0.87
    oleon
    0.85
     eater
    0.84
     hunger
    0.82
     hungry
    0.77
    acy
    0.76
     craving
    0.75
    avascript
    0.75
    ibal
    0.74
    Activations Density 0.007%

    No Known Activations