© 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. 4-RES-JB
    11. 20531
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, politicians, and controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams and their scheduling

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

    No Comments

    Negative Logits
    Published
    -0.71
    formerly
    -0.59
     Interior
    -0.59
    COMPLE
    -0.58
     Associated
    -0.56
    xtap
    -0.55
    Detailed
    -0.55
    ielding
    -0.54
    utterstock
    -0.54
     southeastern
    -0.54
    POSITIVE LOGITS
     âĢ¦"
    1.09
    )."
    1.07
    âĢ¦."
    0.98
    âĢ¦"
    0.98
    !"
    0.97
    .")
    0.94
    ?"
    0.93
     ..."
    0.93
    ?".
    0.91
    ?!"
    0.90
    Activations Density 2.265%

    No Known Activations