© 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. 0-RES-JB
    11. 13463
    Prev
    Next
    INDEX
    Explanations

    phrases related to displaying or showing something prominently

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "displayed" and related forms

    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
     Kinder
    -0.72
    ranch
    -0.64
    ibus
    -0.63
    alg
    -0.61
    co
    -0.61
    jah
    -0.58
    cos
    -0.58
     lawsuits
    -0.57
    soc
    -0.57
     Migration
    -0.57
    POSITIVE LOGITS
     displayed
    3.46
     exhibited
    2.42
     displaying
    2.04
     display
    2.03
     displays
    1.98
     showcased
    1.87
     shown
    1.82
    display
    1.56
     demonstrated
    1.53
     Display
    1.52
    Activations Density 0.013%

    No Known Activations