© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 16905
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate an event or action happening sooner rather than later

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating the concept of time, particularly in relation to the word "sooner."

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

    No Comments

    Negative Logits
    Ward
    -0.74
    square
    -0.74
    prison
    -0.72
    ports
    -0.67
    mir
    -0.66
    port
    -0.66
    me
    -0.65
    ple
    -0.65
    sur
    -0.64
    dust
    -0.63
    POSITIVE LOGITS
     than
    0.98
     confir
    0.87
    aneously
    0.87
     msec
    0.81
     "$:/
    0.79
     Than
    0.79
     nodd
    0.77
     sooner
    0.75
    than
    0.74
    nown
    0.71
    Activations Density 0.009%

    No Known Activations