© 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. 0-RES-JB
    11. 8216
    Prev
    Next
    INDEX
    Explanations

    instances of the word "uber."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "uber" and related concepts

    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
     dispos
    -0.69
     Shoals
    -0.64
     facts
    -0.62
     known
    -0.62
     Snake
    -0.61
     fields
    -0.59
     Iz
    -0.59
     fabrication
    -0.59
     shapes
    -0.59
     categories
    -0.58
    POSITIVE LOGITS
    uber
    4.69
    ub
    1.27
    Uber
    1.24
    ube
    1.23
     uber
    1.17
    ubes
    1.08
    asper
    1.04
    ubs
    1.03
    uper
    1.03
    orbit
    0.99
    Activations Density 0.016%

    No Known Activations