© 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. 9-RES-JB
    11. 17761
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate superlatives or extremes, such as "the oldest," "the highest," or "the largest."

    oai_token-act-pair · gpt-3.5-turbo

    the presence of "the" with high frequency, indicating a focus on definitive articles and their significance in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     aloud
    -0.74
    earch
    -0.69
    uate
    -0.66
    test
    -0.64
    lins
    -0.64
     whence
    -0.60
    arthed
    -0.60
    lations
    -0.59
    Activ
    -0.59
    uberty
    -0.58
    POSITIVE LOGITS
     widest
    1.04
     capability
    1.03
     distinction
    1.03
     advantage
    1.02
     lowest
    1.02
     highest
    1.00
     same
    1.00
     utmost
    1.00
     ability
    0.97
     largest
    0.96
    Activations Density 0.108%

    No Known Activations