© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 2819
    Prev
    Next
    INDEX
    Explanations

    proper nouns indicating individuals and their actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "had."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "had"

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bridge
    -0.64
     Which
    -0.60
    âϦ
    -0.60
     Conclusion
    -0.59
     trope
    -0.58
    PI
    -0.56
    orph
    -0.56
    cious
    -0.55
    VT
    -0.55
    BUG
    -0.54
    POSITIVE LOGITS
     been
    1.22
     previously
    1.12
    iths
    1.05
     undergone
    1.05
     hoped
    1.03
     begun
    1.03
     originally
    1.01
     flown
    0.98
     unsuccessfully
    0.94
    been
    0.92
    Activations Density 0.140%

    No Known Activations