© 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. 10-RES-JB
    11. 18593
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal opinions or declarations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express personal opinions or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estern
    -0.72
    ulent
    -0.68
    artments
    -0.66
    Loading
    -0.62
    poons
    -0.62
    pes
    -0.61
     Written
    -0.61
    Newsletter
    -0.61
    poon
    -0.61
    Ku
    -0.60
    POSITIVE LOGITS
     goodbye
    1.43
     hello
    1.09
     Goodbye
    1.02
     congratulations
    0.98
     thank
    0.95
     congr
    0.92
     farewell
    0.91
     that
    0.90
     unequivocally
    0.89
     THANK
    0.88
    Activations Density 0.075%

    No Known Activations