© 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. 2-RES-JB
    11. 3086
    Prev
    Next
    INDEX
    Explanations

    words related to specific brand names or titles, specifically "Lucky Peach"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "luck" and its associated themes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arians
    -0.79
    ueller
    -0.74
    istration
    -0.73
    merce
    -0.73
    igate
    -0.73
    aciously
    -0.72
    ulates
    -0.71
    arag
    -0.71
    ucl
    -0.69
    IAL
    -0.69
    POSITIVE LOGITS
     Planet
    1.09
     Hearts
    1.03
     Wings
    1.03
     Dreams
    1.02
     Heart
    1.01
     Girl
    0.98
     Birds
    0.97
     Eye
    0.97
     Panda
    0.95
     Guys
    0.94
    Activations Density 0.062%

    No Known Activations