© 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. 10-RES-JB
    11. 16024
    Prev
    Next
    INDEX
    Explanations

    the word "Upon" followed by situations or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "upon" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.87
    Ñĭ
    -0.83
    rams
    -0.81
    apes
    -0.79
    姫
    -0.78
    æ©
    -0.77
    rosse
    -0.76
    ãĥ³ãĤ¸
    -0.75
    DragonMagazine
    -0.75
    inx
    -0.73
    POSITIVE LOGITS
     arrival
    1.58
     completion
    1.41
     receipt
    1.25
     encountering
    1.20
     entering
    1.15
     arriving
    1.15
     realizing
    1.12
     discovering
    1.12
     reaching
    1.11
     returning
    1.09
    Activations Density 0.048%

    No Known Activations