© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7528
    Prev
    Next
    INDEX
    Explanations

    the word "Buddy" or variations of it, such as "buddy" or "Buddy" with different levels of emphasis.

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Buddy" and its variations, indicating a focus on friendship or camaraderie

    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
    ators
    -0.86
    sen
    -0.85
    orius
    -0.82
    inth
    -0.81
    ivation
    -0.77
    ATOR
    -0.77
    apers
    -0.75
    ision
    -0.75
    ournal
    -0.75
    ined
    -0.75
    POSITIVE LOGITS
     buddy
    1.05
     Holly
    1.03
     Buddy
    0.95
     buddies
    0.83
     Faw
    0.75
    illac
    0.74
     Ples
    0.70
     Bobby
    0.69
    busters
    0.68
     McGee
    0.68
    Activations Density 0.011%

    No Known Activations