© 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. 5322
    Prev
    Next
    INDEX
    Explanations

    sketches or drawings

    oai_token-act-pair · gpt-3.5-turbo

    references to sketches and artistic representations

    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
    MO
    -0.69
     Lions
    -0.64
    payer
    -0.64
     Fallen
    -0.64
    immune
    -0.62
    aea
    -0.62
    ighth
    -0.61
    Ga
    -0.60
    Dom
    -0.60
    righteous
    -0.60
    POSITIVE LOGITS
     sketch
    3.97
     sketches
    3.06
     Sketch
    2.24
     sket
    1.89
     drawing
    1.34
     caricature
    1.22
     drawings
    1.22
     improv
    1.16
     schematic
    1.16
     painting
    1.12
    Activations Density 0.015%

    No Known Activations