© 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. 8-RES-JB
    11. 17198
    Prev
    Next
    INDEX
    Explanations

    references to the concept of the "soul" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "soul" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Occupations
    -0.70
     Pearce
    -0.70
     Riyadh
    -0.67
     Conan
    -0.64
     Zucker
    -0.64
    berman
    -0.63
    kson
    -0.62
     Kaplan
    -0.61
     Simpson
    -0.61
     Obst
    -0.60
    POSITIVE LOGITS
    mate
    1.00
    ful
    0.96
    sword
    0.89
    blade
    0.89
     mate
    0.87
    mates
    0.87
    fish
    0.85
    stones
    0.84
    mass
    0.84
     gem
    0.83
    Activations Density 0.030%

    No Known Activations