© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 2897
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Upper" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    words related to a certain type of container or vessel, specifically for holding or transporting liquids or materials

    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
     Dream
    -0.69
     Habit
    -0.68
     bidding
    -0.62
     Chapters
    -0.60
     incon
    -0.60
     evid
    -0.58
     manifestations
    -0.58
    DOC
    -0.58
     disclaim
    -0.57
     Balance
    -0.57
    POSITIVE LOGITS
    pper
    4.48
    ppers
    3.24
    pping
    1.99
    pped
    1.83
    ppings
    1.59
    ppy
    1.55
    ffee
    1.34
    ppe
    1.34
    pton
    1.33
    pperc
    1.32
    Activations Density 0.017%

    No Known Activations