© 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. 4-RES-JB
    11. 810
    Prev
    Next
    INDEX
    Explanations

    expressions emphasizing comparison or connection between different elements or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss comparisons or connections involving the concept of "relation."

    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
    UFF
    -0.84
    ECK
    -0.80
    fly
    -0.74
    oker
    -0.73
    avorite
    -0.72
    ucket
    -0.70
    ahi
    -0.70
    uff
    -0.70
    redited
    -0.69
     straw
    -0.67
    POSITIVE LOGITS
     relation
    0.87
    ability
    0.84
    hips
    0.81
    ality
    0.80
     relations
    0.74
    ativity
    0.73
    gradient
    0.72
    liness
    0.72
    ally
    0.72
    ually
    0.69
    Activations Density 0.015%

    No Known Activations