© 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. 11-RES-JB
    11. 20488
    Prev
    Next
    INDEX
    Explanations

    phrases related to existentialism and philosophical concepts

    oai_token-act-pair · gpt-3.5-turbo

    themes of existential questioning and the futility of existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.79
    Awesome
    -0.75
    umbn
    -0.73
     HUGE
    -0.71
    Yep
    -0.68
    assy
    -0.68
     DRAG
    -0.67
    thumbnails
    -0.66
    Lots
    -0.66
    assic
    -0.66
    POSITIVE LOGITS
     slightest
    1.12
     vain
    1.08
     nor
    1.02
    ught
    1.00
     doubt
    0.98
     unworthy
    0.98
     hereafter
    0.94
    soever
    0.93
     fors
    0.92
     thou
    0.92
    Activations Density 0.247%

    No Known Activations