Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 16345
    Prev
    Next
    INDEX
    Explanations

    words related to modesty or humble beginnings

    oai_token-act-pair · gpt-3.5-turbo

    references to humility and modesty

    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
    emis
    -0.85
    oldown
    -0.76
    alez
    -0.75
    papers
    -0.70
    onz
    -0.69
    ubric
    -0.68
     largeDownload
    -0.68
    ophen
    -0.67
     negatively
    -0.66
     Traff
    -0.65
    POSITIVE LOGITS
     beginnings
    1.18
     consolation
    0.88
    bly
    0.85
    minded
    0.82
     humble
    0.80
     minded
    0.76
    ly
    0.75
    pic
    0.74
     upbringing
    0.70
     Courage
    0.69
    Activations Density 0.040%

    No Known Activations