© 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. 0-RES-JB
    11. 8353
    Prev
    Next
    INDEX
    Explanations

    mentions of intelligence or intelligent actions in the context of various scenarios

    oai_token-act-pair · gpt-3.5-turbo

    mentions of intelligence or the concept of being intelligent

    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
    gren
    -0.76
    yan
    -0.75
    bley
    -0.72
    fold
    -0.67
     Nationals
    -0.67
     Bund
    -0.65
    pal
    -0.65
    git
    -0.64
    hs
    -0.64
    washing
    -0.64
    POSITIVE LOGITS
     intelligent
    3.48
    elligent
    2.64
     Intelligent
    2.59
     smarter
    1.84
     intellig
    1.77
     smart
    1.62
     smartest
    1.54
     sentient
    1.53
     thoughtful
    1.48
     educated
    1.33
    Activations Density 0.018%

    No Known Activations