© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15264
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities with the last name "Wheeler" or "Dolphins."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and entities related to sports, particularly focusing on "Wheeler" and "Dolphins"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CST
    -0.97
     guiActiveUn
    -0.91
     Assy
    -0.87
    sold
    -0.80
     wagon
    -0.79
    cult
    -0.77
     sob
    -0.75
     Spart
    -0.74
     Burg
    -0.73
    bag
    -0.72
    POSITIVE LOGITS
     Dolphins
    2.21
     Dolphin
    1.81
     Hurricanes
    1.62
     dolphins
    1.59
    olphins
    1.59
     Wheeler
    1.53
     dolphin
    1.51
     Marlins
    1.45
     Aj
    1.37
     Epstein
    1.27
    Activations Density 0.043%

    No Known Activations