© 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. 16131
    Prev
    Next
    INDEX
    Explanations

    the word "Until" at the beginning of sentences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "until."

    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
    pour
    -0.70
    chuk
    -0.67
    serv
    -0.61
    Feed
    -0.60
    eny
    -0.59
    oyle
    -0.58
    ullivan
    -0.57
    ettings
    -0.56
    onym
    -0.56
    arious
    -0.55
    POSITIVE LOGITS
     recently
    1.08
     now
    0.90
     lately
    0.88
     proven
    0.87
     then
    0.83
    rely
    0.76
     NOW
    0.75
     2009
    0.73
     July
    0.73
     October
    0.72
    Activations Density 0.032%

    No Known Activations