© 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. 1-RES-JB
    11. 22333
    Prev
    Next
    INDEX
    Explanations

    words related to modesty or humility

    oai_token-act-pair · gpt-3.5-turbo

    references to humility or being humble

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.79
    ammy
    -0.78
    */(
    -0.78
    alez
    -0.72
    NetMessage
    -0.71
     Nanto
    -0.69
    runs
    -0.67
     POL
    -0.67
    oother
    -0.65
    ogh
    -0.65
    POSITIVE LOGITS
     humble
    1.28
    bly
    1.02
     beginnings
    0.86
     tract
    0.81
    bling
    0.78
     lowly
    0.76
    ãĤ©
    0.74
     hum
    0.74
     humility
    0.74
     toast
    0.73
    Activations Density 0.006%

    No Known Activations