© 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. 11964
    Prev
    Next
    INDEX
    Explanations

    instances where actions or processes are beginning or starting

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "begin" in various contexts

    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
     Lives
    -0.66
    judicial
    -0.58
    į
    -0.57
    bal
    -0.57
    rider
    -0.55
    uded
    -0.55
    olan
    -0.53
    atti
    -0.53
     CPC
    -0.52
    etry
    -0.52
    POSITIVE LOGITS
     begin
    3.40
     commence
    2.28
     start
    2.13
     begins
    2.10
    begin
    1.95
     begun
    1.86
     beginning
    1.78
    Begin
    1.76
     began
    1.71
    EGIN
    1.68
    Activations Density 0.015%

    No Known Activations