© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7076
    Prev
    Next
    INDEX
    Explanations

    different types of hairstyles

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to hairstyles, child sexual abuse, goaltending in sports, and electromagnetism

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

    No Comments

    Negative Logits
     Feast
    -0.83
    Interstitial
    -0.72
    hood
    -0.70
    backer
    -0.69
    BSD
    -0.66
    hof
    -0.66
     Maid
    -0.65
     Shed
    -0.64
    ware
    -0.62
    crop
    -0.61
    POSITIVE LOGITS
    ILLE
    0.98
    ancies
    0.93
    ij
    0.91
    yle
    0.90
    ritten
    0.89
    rovers
    0.89
    rast
    0.87
    raph
    0.87
    elines
    0.86
    ör
    0.86
    Activations Density 0.038%

    No Known Activations