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. 0-RES-JB
    6. 2983
    Prev
    Next
    INDEX
    Explanations

    words related to items stored in the fridge or freezer

    oai_token-act-pair · gpt-3.5-turbo

    mentions of refrigerators and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chet
    -0.86
     Burton
    -0.78
    zek
    -0.73
    adow
    -0.73
     Zam
    -0.72
    ted
    -0.69
    edged
    -0.69
     Malone
    -0.68
    words
    -0.68
    idas
    -0.68
    POSITIVE LOGITS
     fridge
    3.67
     refrigerator
    3.36
     freezer
    2.38
     refriger
    2.26
    riger
    1.71
     microwave
    1.21
     cellar
    1.11
     centrif
    1.07
    idges
    1.06
     heater
    1.03
    Activations Density 0.031%

    No Known Activations