© 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
    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. 20457
    Prev
    Next
    INDEX
    Explanations

    relationships or concepts that fall under an all-encompassing or umbrella term

    oai_token-act-pair · gpt-3.5-turbo

    the term "umbrella" in various contexts, often used metaphorically to represent inclusivity or overarching 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
    Submit
    -0.69
    Jones
    -0.67
    ued
    -0.66
    conv
    -0.66
     Tenn
    -0.65
     conversions
    -0.63
     Cooking
    -0.62
     bots
    -0.62
     Jones
    -0.62
     Khan
    -0.61
    POSITIVE LOGITS
     umbrella
    4.20
     umb
    1.87
     Umb
    1.36
     encomp
    1.26
    rella
    1.19
    aceae
    1.11
     banner
    1.06
     acronym
    1.06
     ausp
    1.02
     encompass
    1.00
    Activations Density 0.024%

    No Known Activations