© 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. 11-RES-JB
    6. 9525
    Prev
    Next
    INDEX
    Explanations

    complex phrases or descriptions that involve a mixture of positive and negative attributes or actions

    oai_token-act-pair · gpt-3.5-turbo

    complex narrative structures and clever tactics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eph
    -0.75
    reports
    -0.75
    izons
    -0.73
     Views
    -0.73
     Libraries
    -0.72
    mbuds
    -0.72
    rane
    -0.70
    amples
    -0.70
    isters
    -0.69
     Areas
    -0.68
    POSITIVE LOGITS
     ploy
    1.58
     prank
    1.43
     scheme
    1.39
     stunt
    1.39
     disguise
    1.37
     plot
    1.33
     deception
    1.30
     trick
    1.29
     miracle
    1.27
     plan
    1.24
    Activations Density 0.531%

    No Known Activations