© 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. 4-RES-JB
    11. 7030
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "getting" or "becoming."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "getting" in various contexts

    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
    manship
    -0.69
    ridge
    -0.68
    deen
    -0.64
     Britann
    -0.63
    velt
    -0.59
    olini
    -0.58
     Vide
    -0.58
    mare
    -0.57
    mount
    -0.57
    ively
    -0.57
    POSITIVE LOGITS
     rid
    1.20
     acquainted
    0.94
     Started
    0.85
    tin
    0.84
    TING
    0.81
    cloneembedreportprint
    0.77
     away
    0.77
    acqu
    0.77
     distracted
    0.76
     bored
    0.76
    Activations Density 0.032%

    No Known Activations