© 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. 1-RES-JB
    11. 21483
    Prev
    Next
    INDEX
    Explanations

    mentions of olives, especially with high emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to olives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lord
    -0.63
    Gi
    -0.62
     chromosome
    -0.61
    Brand
    -0.61
    rises
    -0.60
     fuss
    -0.57
     motion
    -0.55
     Mysteries
    -0.55
     disability
    -0.55
    akuya
    -0.54
    POSITIVE LOGITS
    ives
    1.47
    ynthesis
    1.02
    IVE
    0.95
    IVES
    0.90
    ystem
    0.89
    terday
    0.86
    ynt
    0.81
    atives
    0.81
    matter
    0.80
    hops
    0.79
    Activations Density 0.008%

    No Known Activations