© 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. 7-RES-JB
    11. 1868
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'been'

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "there have been" which indicates occurrences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arta
    -0.88
    arily
    -0.68
    would
    -0.67
     Taxes
    -0.66
    ribe
    -0.65
    poses
    -0.64
    Imagine
    -0.62
    ooter
    -0.62
     Imagine
    -0.61
    ooters
    -0.59
    POSITIVE LOGITS
     plenty
    0.91
    cffffcc
    0.82
     murm
    0.79
     unanimous
    0.77
     enough
    0.75
     tremendous
    0.69
     concerted
    0.69
     ample
    0.68
     speculation
    0.66
    ļé
    0.65
    Activations Density 0.022%

    No Known Activations