© 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. 10239
    Prev
    Next
    INDEX
    Explanations

    instances of the word "just" used for emphasis in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "just" used to emphasize or downplay statements

    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
    antage
    -0.79
    elist
    -0.68
    aphael
    -0.66
    ixel
    -0.62
    ctr
    -0.59
    pora
    -0.58
     subsequ
    -0.58
    ourse
    -0.58
    cod
    -0.57
    atching
    -0.57
    POSITIVE LOGITS
     plain
    0.98
     happened
    0.97
     couldn
    0.97
     ain
    0.97
    ifiable
    0.92
     gotta
    0.91
    ifications
    0.90
     wanna
    0.87
     wasn
    0.87
     happens
    0.86
    Activations Density 0.058%

    No Known Activations