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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 17833
    Prev
    Next
    INDEX
    Explanations

    names of famous philosophers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of philosophers and philosophical concepts

    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
     Ribbon
    -0.74
     Park
    -0.74
    Park
    -0.74
     Chaff
    -0.73
    estation
    -0.72
     SAF
    -0.71
     PHOTO
    -0.71
    rero
    -0.70
     Kodi
    -0.70
     Ginger
    -0.70
    POSITIVE LOGITS
     philosophers
    2.63
     philosopher
    2.35
     Hegel
    2.12
     philosophical
    1.99
     Nietzsche
    1.97
     philosoph
    1.84
     Aristotle
    1.83
     metaphysical
    1.82
     Socrates
    1.79
     Kant
    1.79
    Activations Density 0.097%

    No Known Activations