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. 11-RES-JB
    6. 19671
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases emphasizing philosophical or existential contemplation

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding existential questions and philosophical discussions about purpose

    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
     tipped
    -0.77
     scrim
    -0.73
    daq
    -0.73
     spotlight
    -0.71
    creen
    -0.70
     offic
    -0.69
     rollout
    -0.68
     billed
    -0.68
     nationwide
    -0.68
     rented
    -0.68
    POSITIVE LOGITS
    Therefore
    1.38
    Thus
    1.35
     Therefore
    1.24
     Hence
    1.23
     Suppose
    1.21
     Thus
    1.20
     Aristotle
    1.09
    Furthermore
    1.09
    §
    1.05
     Consequently
    1.05
    Activations Density 0.463%

    No Known Activations