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. 9319
    Prev
    Next
    INDEX
    Explanations

    the word "baked" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    words related to food preparation methods, specifically baking

    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
     words
    -0.65
     guild
    -0.63
     production
    -0.60
    WOR
    -0.59
     Garcia
    -0.59
     frequency
    -0.59
     WOR
    -0.58
     duties
    -0.58
     forum
    -0.58
     Cham
    -0.56
    POSITIVE LOGITS
    aked
    4.30
    aking
    2.45
    aks
    1.99
    aky
    1.82
    aker
    1.60
    akers
    1.57
    akes
    1.53
    ake
    1.42
    AKING
    1.36
    akable
    1.35
    Activations Density 0.006%

    No Known Activations