© 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. 1527
    Prev
    Next
    INDEX
    Explanations

    instances of the word "all" followed by a high level of urgency or intensity

    oai_token-act-pair · gpt-3.5-turbo

    the term "all" as a concept or phrase

    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
     slightly
    -0.63
     respected
    -0.61
     basis
    -0.60
     Tec
    -0.59
     tem
    -0.59
     equivalents
    -0.59
     fallout
    -0.55
     dod
    -0.55
     equivalent
    -0.55
     timely
    -0.55
    POSITIVE LOGITS
    all
    4.07
    alls
    2.57
    ALL
    2.26
    allion
    1.95
    alling
    1.90
    alled
    1.73
    alla
    1.72
    allo
    1.70
    allic
    1.57
    All
    1.53
    Activations Density 0.018%

    No Known Activations