© 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. 3-RES-JB
    11. 522
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Lucubrate" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific type of food or plant, particularly cucurbits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.83
    åĤ
    -0.78
    âĶģ
    -0.70
    senal
    -0.70
     Avalon
    -0.69
     Payton
    -0.65
    Dispatch
    -0.65
    ħĭ
    -0.64
     CPS
    -0.64
     Sawyer
    -0.64
    POSITIVE LOGITS
    hess
    1.10
    ierrez
    1.02
    kered
    1.01
    ourt
    0.98
    reme
    0.97
    inations
    0.96
    urrent
    0.96
    razy
    0.96
    inic
    0.95
    otiation
    0.94
    Activations Density 0.008%

    No Known Activations